[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-6b2accfa125e6e3e-pick-gemma-4-model-by-hardware-to-unlock-9-10-math-summary":3,"summaries-facets-categories":126,"summary-related-6b2accfa125e6e3e-pick-gemma-4-model-by-hardware-to-unlock-9-10-math-summary":3711},{"id":4,"title":5,"ai":6,"body":13,"categories":60,"created_at":62,"date_modified":62,"description":54,"extension":63,"faq":62,"featured":64,"kicker_label":62,"meta":65,"navigation":108,"path":109,"published_at":110,"question":62,"scraped_at":111,"seo":112,"sitemap":113,"source_id":114,"source_name":115,"source_type":116,"source_url":117,"stem":118,"tags":119,"thumbnail_url":62,"tldr":123,"tweet":62,"unknown_tags":124,"__hash__":125},"summaries\u002Fsummaries\u002F6b2accfa125e6e3e-pick-gemma-4-model-by-hardware-to-unlock-9-10-math-summary.md","Pick Gemma 4 Model by Hardware to Unlock 9\u002F10 Math Accuracy",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","x-ai\u002Fgrok-4.1-fast",6736,2210,15095,0.00242955,{"type":14,"value":15,"toc":53},"minimark",[16,21,25,28,32,35,38,42,50],[17,18,20],"h2",{"id":19},"hardware-matched-model-selection-maximizes-performance","Hardware-Matched Model Selection Maximizes Performance",[22,23,24],"p",{},"Gemma 4 offers four variants tailored to hardware tiers, preventing the common error of loading oversized models that seem \"broken\" due to memory shortages or slow inference. E2B (2.3B params, 3-5GB RAM) fits phones and Raspberry Pi 5 (5 tokens\u002Fsec chatting speed), prioritizing privacy for summaries\u002Fquick replies over complex coding—Google embeds it in future Pixels. E4B (4.5B params, 5-6GB) suits 8-16GB laptops like MacBook Air, handling multimodal inputs (audio\u002Fimages) for local chat\u002Fdocument Q&A but falters on multi-step agents. The 26B MoE model activates only 4B params at once (16-18GB load, plan 24GB total), delivering flagship quality at 4B-model speed with 250k token context—ranks #6 on LMSYS Arena open models. Flagship 31B (30B params, 17-20GB weights + headroom to 24GB VRAM) tops at #3 open on Arena, hits 89% on Olympiad math\u002Fcompetitive programming (master-level), and beats larger closed models like Claude Sonnet on agentic business sims—ideal for workstations with NVIDIA\u002FApple Silicon.",[22,26,27],{},"Decision tree: Phones\u002FPi → E2B; 8-16GB laptops → E4B; 24GB system → 26B; 24GB+ VRAM\u002FMac 32GB → 31B. Avoid aggressive quantization on MoE models, as it tanks quality.",[17,29,31],{"id":30},"benchmarks-show-massive-gains-but-real-world-speed-needs-tricks","Benchmarks Show Massive Gains, But Real-World Speed Needs Tricks",[22,33,34],{},"Gemma 4 leaps year-over-year: prior small models solved 1-in-5 math problems; now 9-in-10 across sizes. 31B matches Qwen 3.5\u002FKimi K2.5 head-to-head on Arena despite fewer active params via MoE. Strong for one-shot coding\u002Fmath (beats most humans on programming sites) but skip for long tool-call chains—closed models edge it on chained agents.",[22,36,37],{},"Free 29% speed boost (50% on code): Pair 31B drafter with E2B guesser via speculative decoding (shared vocab enables it), loading both in 24GB. Use LM Studio's advanced docs for setup. This yields production speeds without hardware upgrades, turning flagship quality into practical desktop use.",[17,39,41],{"id":40},"essential-tools-and-fixes-for-reliable-local-runs","Essential Tools and Fixes for Reliable Local Runs",[22,43,44,45,49],{},"Run offline\u002Fprivate on any OS: Windows\u002FMac → Ollama (one-line install: ",[46,47,48],"code",{},"ollama run gemma4",") or LM Studio (GUI chat); Linux → same + llama.cpp\u002FvLLM for 31B speed squeezes; Phones → E2B via dedicated mobile guides.",[22,51,52],{},"Three fixes avoid early adopter pitfalls: (1) Use latest file formats\u002Fruntime—initial uploads had tokenizer bug (garbled text\u002Ftool calls, fixed in llama.cpp PR #21343 or re-uploads). (2) Stick to baked-in settings (e.g., Google's recommended temp\u002Fsampling). (3) For looped tool calls, test community tweaks for agent reliability. Unsloth Hugging Face quants help load times. All under Apache 2.0, multimodal-ready, setup \u003C10min.",{"title":54,"searchDepth":55,"depth":55,"links":56},"",2,[57,58,59],{"id":19,"depth":55,"text":20},{"id":30,"depth":55,"text":31},{"id":40,"depth":55,"text":41},[61],"AI & LLMs",null,"md",false,{"content_references":66,"triage":103},[67,73,77,81,84,87,90,94,97,100],{"type":68,"title":69,"author":70,"url":71,"context":72},"report","Gemma 4 announcement","Google","https:\u002F\u002Fblog.google\u002Ftechnology\u002Fdevelopers\u002Fgemma-4\u002F","mentioned",{"type":68,"title":74,"author":75,"url":76,"context":72},"Gemma 4 model card","Google AI","https:\u002F\u002Fai.google.dev\u002Fgemma\u002Fdocs\u002Fcore\u002Fmodel_card_4",{"type":78,"title":79,"url":80,"context":72},"tool","Ollama","https:\u002F\u002Follama.com",{"type":78,"title":82,"url":83,"context":72},"LM Studio","https:\u002F\u002Flmstudio.ai",{"type":78,"title":85,"url":86,"context":72},"llama.cpp","https:\u002F\u002Fgithub.com\u002Fggml-org\u002Fllama.cpp",{"type":78,"title":88,"url":89,"context":72},"vLLM","https:\u002F\u002Fdocs.vllm.ai",{"type":91,"title":92,"url":93,"context":72},"other","LMArena leaderboard","https:\u002F\u002Flmarena.ai",{"type":78,"title":95,"url":96,"context":72},"Unsloth re-quants","https:\u002F\u002Fhuggingface.co\u002Funsloth",{"type":91,"title":98,"url":99,"context":72},"llama.cpp tokenizer fix (PR #21343)","https:\u002F\u002Fgithub.com\u002Fggml-org\u002Fllama.cpp\u002Fpull\u002F21343",{"type":91,"title":101,"url":102,"context":72},"LM Studio speculative decoding docs","https:\u002F\u002Flmstudio.ai\u002Fdocs\u002Fapp\u002Fadvanced\u002Fspeculative-decoding",{"relevance":104,"novelty":105,"quality":104,"actionability":104,"composite":106,"reasoning":107},4,3,3.8,"Category: AI & LLMs. The article provides specific insights into selecting AI models based on hardware capabilities, addressing the audience's need for practical applications in building AI-powered products. It includes actionable advice on pairing models for performance boosts, which is directly applicable to developers and founders.",true,"\u002Fsummaries\u002F6b2accfa125e6e3e-pick-gemma-4-model-by-hardware-to-unlock-9-10-math-summary","2026-04-19 21:52:44","2026-04-21 15:22:05",{"title":5,"description":54},{"loc":109},"b698467bc8ca5e8d","DIY Smart Code","article","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=SLOqlEmuy5U","summaries\u002F6b2accfa125e6e3e-pick-gemma-4-model-by-hardware-to-unlock-9-10-math-summary",[120,121,122],"llm","ai-tools","open-source","Gemma 4's four models—E2B (3-5GB phone), E4B (5-6GB laptop), 26B MoE (16-18GB mid-tier), 31B (20-24GB flagship)—jump math benchmarks from 1\u002F5 to 9\u002F10 correct. Pair 31B+E2B for 29% speed boost. Use Ollama\u002FLM Studio for easy local runs.",[],"ua65HuwxIouruqLL41l8OC1Al-b2RnWySeAG_lZ4SOA",[127,130,133,135,138,141,143,145,147,149,151,153,156,158,160,162,164,166,168,170,172,174,177,180,182,184,187,189,191,194,196,198,200,202,204,206,208,210,212,214,216,218,220,222,224,226,228,230,232,234,236,238,240,242,244,246,248,250,252,254,256,258,260,262,264,266,268,270,272,274,276,278,280,282,284,286,288,290,292,294,296,298,300,302,304,306,308,310,312,314,316,318,320,322,324,326,328,330,332,334,336,338,340,342,344,346,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,451,453,455,457,459,461,463,465,467,469,471,473,475,477,479,481,483,485,487,489,491,493,495,497,499,501,503,505,507,509,511,513,515,517,519,521,523,525,527,529,531,533,535,537,539,541,543,545,547,549,551,553,555,557,559,561,563,565,567,569,571,573,575,577,579,581,583,585,587,589,591,593,595,597,599,601,603,605,607,609,611,613,615,617,619,621,623,625,627,629,631,633,635,637,639,641,643,645,647,649,651,653,655,657,659,661,663,665,667,669,671,673,675,677,679,681,683,685,687,689,691,693,695,697,699,701,703,705,707,709,711,713,715,717,719,721,723,725,727,729,731,733,735,737,739,741,743,745,747,749,751,753,755,757,759,761,763,765,767,769,771,773,775,777,779,781,783,785,787,789,791,793,795,797,799,801,803,805,807,809,811,813,815,817,819,821,823,825,827,829,831,833,835,837,839,841,843,845,847,849,851,853,855,857,859,861,863,865,867,869,871,873,875,877,879,881,883,885,887,889,891,893,895,897,899,901,903,905,907,909,911,913,915,917,919,921,923,925,927,929,931,933,935,937,939,941,943,945,947,949,951,953,955,957,959,961,963,965,967,969,971,973,975,977,979,981,983,985,987,989,991,993,995,997,999,1001,1003,1005,1007,1009,1011,1013,1015,1017,1019,1021,1023,1025,1027,1029,1031,1033,1035,1037,1039,1041,1043,1045,1047,1049,1051,1053,1055,1057,1059,1061,1063,1065,1067,1069,1071,1073,1075,1077,1079,1081,1083,1085,1087,1089,1091,1093,1095,1097,1099,1101,1103,1105,1107,1109,1111,1113,1115,1117,1119,1121,1123,1125,1127,1129,1131,1133,1135,1137,1139,1141,1143,1145,1147,1149,1151,1153,1155,1157,1159,1161,1163,1165,1167,1169,1171,1173,1175,1177,1179,1181,1183,1185,1187,1189,1191,1193,1195,1197,1199,1201,1203,1205,1207,1209,1211,1213,1215,1217,1219,1221,1223,1225,1227,1229,1231,1233,1235,1237,1239,1241,1243,1245,1247,1249,1251,1253,1255,1257,1259,1261,1263,1265,1267,1269,1271,1273,1275,1277,1279,1281,1283,1285,1287,1289,1291,1293,1295,1297,1299,1301,1303,1305,1307,1309,1311,1313,1315,1317,1319,1321,1323,1325,1327,1329,1331,1333,1335,1337,1339,1341,1343,1345,1347,1349,1351,1353,1355,1357,1359,1361,1363,1365,1367,1369,1371,1373,1375,1377,1379,1381,1383,1385,1387,1389,1391,1393,1395,1397,1399,1401,1403,1405,1407,1409,1411,1413,1415,1417,1419,1421,1423,1425,1427,1429,1431,1433,1435,1437,1439,1441,1443,1445,1447,1449,1451,1453,1455,1457,1459,1461,1463,1465,1467,1469,1471,1473,1475,1477,1479,1481,1483,1485,1487,1489,1491,1493,1495,1497,1499,1501,1503,1505,1507,1509,1511,1513,1515,1517,1519,1521,1523,1525,1527,1529,1531,1533,1535,1537,1539,1541,1543,1545,1547,1549,1551,1553,1555,1557,1559,1561,1563,1565,1567,1569,1571,1573,1575,1577,1579,1581,1583,1585,1587,1589,1591,1593,1595,1597,1599,1601,1603,1605,1607,1609,1611,1613,1615,1617,1619,1621,1623,1625,1627,1629,1631,1633,1635,1637,1639,1641,1643,1645,1647,1649,1651,1653,1655,1657,1659,1661,1663,1665,1667,1669,1671,1673,1675,1677,1679,1681,1683,1685,1687,1689,1691,1693,1695,1697,1699,1701,1703,1705,1707,1709,1711,1713,1715,1717,1719,1721,1723,1725,1727,1729,1731,1733,1735,1737,1739,1741,1743,1745,1747,1749,1751,1753,1755,1757,1759,1761,1763,1765,1767,1769,1771,1773,1775,1777,1779,1781,1783,1785,1787,1789,1791,1793,1795,1797,1799,1801,1803,1805,1807,1809,1811,1813,1815,1817,1819,1821,1823,1825,1827,1829,1831,1833,1835,1837,1839,1841,1843,1845,1847,1849,1851,1853,1855,1857,1859,1861,1863,1865,1867,1869,1871,1873,1875,1877,1879,1881,1883,1885,1887,1889,1891,1893,1895,1897,1899,1901,1903,1905,1907,1909,1911,1913,1915,1917,1919,1921,1923,1925,1927,1929,1931,1933,1935,1937,1939,1941,1943,1945,1947,1949,1951,1953,1955,1957,1959,1961,1963,1965,1967,1969,1971,1973,1975,1977,1979,1981,1983,1985,1987,1989,1991,1993,1995,1997,1999,2001,2003,2005,2007,2009,2011,2013,2015,2017,2019,2021,2023,2025,2027,2029,2031,2033,2035,2037,2039,2041,2043,2045,2047,2049,2051,2053,2055,2057,2059,2061,2063,2065,2067,2069,2071,2073,2075,2077,2079,2081,2083,2085,2087,2089,2091,2093,2095,2097,2099,2101,2103,2105,2107,2109,2111,2113,2115,2117,2119,2121,2123,2125,2127,2129,2131,2133,2135,2137,2139,2141,2143,2145,2147,2149,2151,2153,2155,2157,2159,2161,2163,2165,2167,2169,2171,2173,2175,2177,2179,2181,2183,2185,2187,2189,2191,2193,2195,2197,2199,2201,2203,2205,2207,2209,2211,2213,2215,2217,2219,2221,2223,2225,2227,2229,2231,2233,2235,2237,2239,2241,2243,2245,2247,2249,2251,2253,2255,2257,2259,2261,2263,2265,2267,2269,2271,2273,2275,2277,2279,2281,2283,2285,2287,2289,2291,2293,2295,2297,2299,2301,2303,2305,2307,2309,2311,2313,2315,2317,2319,2321,2323,2325,2327,2329,2331,2333,2335,2337,2339,2341,2343,2345,2347,2349,2351,2353,2355,2357,2359,2361,2363,2365,2367,2369,2371,2373,2375,2377,2379,2381,2383,2385,2387,2389,2391,2393,2395,2397,2399,2401,2403,2405,2407,2409,2411,2413,2415,2417,2419,2421,2423,2425,2427,2429,2431,2433,2435,2437,2439,2441,2443,2445,2447,2449,2451,2453,2455,2457,2459,2461,2463,2465,2467,2469,2471,2473,2475,2477,2479,2481,2483,2485,2487,2489,2491,2493,2495,2497,2499,2501,2503,2505,2507,2509,2511,2513,2515,2517,2519,2521,2523,2525,2527,2529,2531,2533,2535,2537,2539,2541,2543,2545,2547,2549,2551,2553,2555,2557,2559,2561,2563,2565,2567,2569,2571,2573,2575,2577,2579,2581,2583,2585,2587,2589,2591,2593,2595,2597,2599,2601,2603,2605,2607,2609,2611,2613,2615,2617,2619,2621,2623,2625,2627,2629,2631,2633,2635,2637,2639,2641,2643,2645,2647,2649,2651,2653,2655,2657,2659,2661,2663,2665,2667,2669,2671,2673,2675,2677,2679,2681,2683,2685,2687,2689,2691,2693,2695,2697,2699,2701,2703,2705,2707,2709,2711,2713,2715,2717,2719,2721,2723,2725,2727,2729,2731,2733,2735,2737,2739,2741,2743,2745,2747,2749,2751,2753,2755,2757,2759,2761,2763,2765,2767,2769,2771,2773,2775,2777,2779,2781,2783,2785,2787,2789,2791,2793,2795,2797,2799,2801,2803,2805,2807,2809,2811,2813,2815,2817,2819,2821,2823,2825,2827,2829,2831,2833,2835,2837,2839,2841,2843,2845,2847,2849,2851,2853,2855,2857,2859,2861,2863,2865,2867,2869,2871,2873,2875,2877,2879,2881,2883,2885,2887,2889,2891,2893,2895,2897,2899,2901,2903,2905,2907,2909,2911,2913,2915,2917,2919,2921,2923,2925,2927,2929,2931,2933,2935,2937,2939,2941,2943,2945,2947,2949,2951,2953,2955,2957,2959,2961,2963,2965,2967,2969,2971,2973,2975,2977,2979,2981,2983,2985,2987,2989,2991,2993,2995,2997,2999,3001,3003,3005,3007,3009,3011,3013,3015,3017,3019,3021,3023,3025,3027,3029,3031,3033,3035,3037,3039,3041,3043,3045,3047,3049,3051,3053,3055,3057,3059,3061,3063,3065,3067,3069,3071,3073,3075,3077,3079,3081,3083,3085,3087,3089,3091,3093,3095,3097,3099,3101,3103,3105,3107,3109,3111,3113,3115,3117,3119,3121,3123,3125,3127,3129,3131,3133,3135,3137,3139,3141,3143,3145,3147,3149,3151,3153,3155,3157,3159,3161,3163,3165,3167,3169,3171,3173,3175,3177,3179,3181,3183,3185,3187,3189,3191,3193,3195,3197,3199,3201,3203,3205,3207,3209,3211,3213,3215,3217,3219,3221,3223,3225,3227,3229,3231,3233,3235,3237,3239,3241,3243,3245,3247,3249,3251,3253,3255,3257,3259,3261,3263,3265,3267,3269,3271,3273,3275,3277,3279,3281,3283,3285,3287,3289,3291,3293,3295,3297,3299,3301,3303,3305,3307,3309,3311,3313,3315,3317,3319,3321,3323,3325,3327,3329,3331,3333,3335,3337,3339,3341,3343,3345,3347,3349,3351,3353,3355,3357,3359,3361,3363,3365,3367,3369,3371,3373,3375,3377,3379,3381,3383,3385,3387,3389,3391,3393,3395,3397,3399,3401,3403,3405,3407,3409,3411,3413,3415,3417,3419,3421,3423,3425,3427,3429,3431,3433,3435,3437,3439,3441,3443,3445,3447,3449,3451,3453,3455,3457,3459,3461,3463,3465,3467,3469,3471,3473,3475,3477,3479,3481,3483,3485,3487,3489,3491,3493,3495,3497,3499,3501,3503,3505,3507,3509,3511,3513,3515,3517,3519,3521,3523,3525,3527,3529,3531,3533,3535,3537,3539,3541,3543,3545,3547,3549,3551,3553,3555,3557,3559,3561,3563,3565,3567,3569,3571,3573,3575,3577,3579,3581,3583,3585,3587,3589,3591,3593,3595,3597,3599,3601,3603,3605,3607,3609,3611,3613,3615,3617,3619,3621,3623,3625,3627,3629,3631,3633,3635,3637,3639,3641,3643,3645,3647,3649,3651,3653,3655,3657,3659,3661,3663,3665,3667,3669,3671,3673,3675,3677,3679,3681,3683,3685,3687,3689,3691,3693,3695,3697,3699,3701,3703,3705,3707,3709],{"categories":128},[129],"Developer Productivity",{"categories":131},[132],"Business & SaaS",{"categories":134},[61],{"categories":136},[137],"AI Automation",{"categories":139},[140],"Product Strategy",{"categories":142},[61],{"categories":144},[129],{"categories":146},[132],{"categories":148},[],{"categories":150},[61],{"categories":152},[],{"categories":154},[155],"AI News & Trends",{"categories":157},[137],{"categories":159},[155],{"categories":161},[137],{"categories":163},[137],{"categories":165},[61],{"categories":167},[61],{"categories":169},[155],{"categories":171},[61],{"categories":173},[],{"categories":175},[176],"Design & Frontend",{"categories":178},[179],"Data Science & Visualization",{"categories":181},[155],{"categories":183},[],{"categories":185},[186],"Software Engineering",{"categories":188},[61],{"categories":190},[137],{"categories":192},[193],"Marketing & Growth",{"categories":195},[61],{"categories":197},[137],{"categories":199},[],{"categories":201},[],{"categories":203},[176],{"categories":205},[137],{"categories":207},[129],{"categories":209},[176],{"categories":211},[61],{"categories":213},[137],{"categories":215},[155],{"categories":217},[],{"categories":219},[],{"categories":221},[137],{"categories":223},[186],{"categories":225},[],{"categories":227},[132],{"categories":229},[],{"categories":231},[],{"categories":233},[137],{"categories":235},[137],{"categories":237},[61],{"categories":239},[],{"categories":241},[186],{"categories":243},[],{"categories":245},[],{"categories":247},[],{"categories":249},[61],{"categories":251},[193],{"categories":253},[176],{"categories":255},[176],{"categories":257},[61],{"categories":259},[137],{"categories":261},[61],{"categories":263},[61],{"categories":265},[137],{"categories":267},[137],{"categories":269},[179],{"categories":271},[155],{"categories":273},[137],{"categories":275},[193],{"categories":277},[137],{"categories":279},[140],{"categories":281},[],{"categories":283},[137],{"categories":285},[],{"categories":287},[137],{"categories":289},[186],{"categories":291},[176],{"categories":293},[61],{"categories":295},[],{"categories":297},[],{"categories":299},[137],{"categories":301},[],{"categories":303},[61],{"categories":305},[],{"categories":307},[129],{"categories":309},[186],{"categories":311},[132],{"categories":313},[155],{"categories":315},[61],{"categories":317},[],{"categories":319},[61],{"categories":321},[],{"categories":323},[186],{"categories":325},[179],{"categories":327},[],{"categories":329},[61],{"categories":331},[176],{"categories":333},[],{"categories":335},[176],{"categories":337},[137],{"categories":339},[],{"categories":341},[137],{"categories":343},[155],{"categories":345},[132],{"categories":347},[61],{"categories":349},[],{"categories":351},[137],{"categories":353},[61],{"categories":355},[140],{"categories":357},[],{"categories":359},[61],{"categories":361},[137],{"categories":363},[137],{"categories":365},[],{"categories":367},[179],{"categories":369},[61],{"categories":371},[],{"categories":373},[129],{"categories":375},[132],{"categories":377},[61],{"categories":379},[137],{"categories":381},[186],{"categories":383},[61],{"categories":385},[],{"categories":387},[],{"categories":389},[61],{"categories":391},[],{"categories":393},[176],{"categories":395},[],{"categories":397},[61],{"categories":399},[],{"categories":401},[137],{"categories":403},[61],{"categories":405},[176],{"categories":407},[],{"categories":409},[61],{"categories":411},[61],{"categories":413},[132],{"categories":415},[137],{"categories":417},[61],{"categories":419},[176],{"categories":421},[137],{"categories":423},[],{"categories":425},[],{"categories":427},[155],{"categories":429},[],{"categories":431},[61],{"categories":433},[132,193],{"categories":435},[],{"categories":437},[61],{"categories":439},[],{"categories":441},[],{"categories":443},[61],{"categories":445},[],{"categories":447},[61],{"categories":449},[450],"DevOps & Cloud",{"categories":452},[],{"categories":454},[155],{"categories":456},[176],{"categories":458},[],{"categories":460},[155],{"categories":462},[155],{"categories":464},[61],{"categories":466},[193],{"categories":468},[],{"categories":470},[132],{"categories":472},[],{"categories":474},[61,450],{"categories":476},[61],{"categories":478},[61],{"categories":480},[137],{"categories":482},[61,186],{"categories":484},[179],{"categories":486},[61],{"categories":488},[193],{"categories":490},[137],{"categories":492},[137],{"categories":494},[],{"categories":496},[137],{"categories":498},[61,132],{"categories":500},[],{"categories":502},[176],{"categories":504},[176],{"categories":506},[],{"categories":508},[],{"categories":510},[155],{"categories":512},[],{"categories":514},[129],{"categories":516},[186],{"categories":518},[61],{"categories":520},[176],{"categories":522},[137],{"categories":524},[186],{"categories":526},[155],{"categories":528},[176],{"categories":530},[],{"categories":532},[61],{"categories":534},[61],{"categories":536},[61],{"categories":538},[155],{"categories":540},[129],{"categories":542},[61],{"categories":544},[137],{"categories":546},[450],{"categories":548},[176],{"categories":550},[137],{"categories":552},[],{"categories":554},[],{"categories":556},[176],{"categories":558},[155],{"categories":560},[179],{"categories":562},[],{"categories":564},[61],{"categories":566},[61],{"categories":568},[132],{"categories":570},[61],{"categories":572},[61],{"categories":574},[155],{"categories":576},[],{"categories":578},[137],{"categories":580},[186],{"categories":582},[],{"categories":584},[61],{"categories":586},[61],{"categories":588},[137],{"categories":590},[],{"categories":592},[],{"categories":594},[61],{"categories":596},[],{"categories":598},[132],{"categories":600},[137],{"categories":602},[],{"categories":604},[129],{"categories":606},[61],{"categories":608},[132],{"categories":610},[155],{"categories":612},[],{"categories":614},[],{"categories":616},[],{"categories":618},[155],{"categories":620},[155],{"categories":622},[],{"categories":624},[],{"categories":626},[132],{"categories":628},[],{"categories":630},[],{"categories":632},[129],{"categories":634},[],{"categories":636},[193],{"categories":638},[137],{"categories":640},[132],{"categories":642},[137],{"categories":644},[186],{"categories":646},[],{"categories":648},[140],{"categories":650},[176],{"categories":652},[186],{"categories":654},[61],{"categories":656},[137],{"categories":658},[132],{"categories":660},[61],{"categories":662},[],{"categories":664},[],{"categories":666},[186],{"categories":668},[179],{"categories":670},[140],{"categories":672},[137],{"categories":674},[61],{"categories":676},[],{"categories":678},[450],{"categories":680},[],{"categories":682},[137],{"categories":684},[],{"categories":686},[],{"categories":688},[61],{"categories":690},[176],{"categories":692},[193],{"categories":694},[137],{"categories":696},[],{"categories":698},[129],{"categories":700},[],{"categories":702},[155],{"categories":704},[61,450],{"categories":706},[155],{"categories":708},[61],{"categories":710},[132],{"categories":712},[61],{"categories":714},[],{"categories":716},[132],{"categories":718},[],{"categories":720},[186],{"categories":722},[176],{"categories":724},[155],{"categories":726},[179],{"categories":728},[129],{"categories":730},[61],{"categories":732},[186],{"categories":734},[],{"categories":736},[],{"categories":738},[140],{"categories":740},[],{"categories":742},[61],{"categories":744},[],{"categories":746},[176],{"categories":748},[176],{"categories":750},[176],{"categories":752},[],{"categories":754},[],{"categories":756},[155],{"categories":758},[137],{"categories":760},[61],{"categories":762},[61],{"categories":764},[61],{"categories":766},[132],{"categories":768},[61],{"categories":770},[],{"categories":772},[186],{"categories":774},[186],{"categories":776},[132],{"categories":778},[],{"categories":780},[61],{"categories":782},[61],{"categories":784},[132],{"categories":786},[155],{"categories":788},[193],{"categories":790},[137],{"categories":792},[],{"categories":794},[176],{"categories":796},[],{"categories":798},[61],{"categories":800},[],{"categories":802},[132],{"categories":804},[137],{"categories":806},[],{"categories":808},[450],{"categories":810},[179],{"categories":812},[186],{"categories":814},[193],{"categories":816},[186],{"categories":818},[137],{"categories":820},[],{"categories":822},[],{"categories":824},[137],{"categories":826},[129],{"categories":828},[137],{"categories":830},[140],{"categories":832},[132],{"categories":834},[],{"categories":836},[61],{"categories":838},[140],{"categories":840},[61],{"categories":842},[61],{"categories":844},[193],{"categories":846},[176],{"categories":848},[137],{"categories":850},[],{"categories":852},[],{"categories":854},[450],{"categories":856},[186],{"categories":858},[],{"categories":860},[137],{"categories":862},[61],{"categories":864},[176,61],{"categories":866},[129],{"categories":868},[],{"categories":870},[61],{"categories":872},[129],{"categories":874},[176],{"categories":876},[137],{"categories":878},[186],{"categories":880},[],{"categories":882},[61],{"categories":884},[],{"categories":886},[129],{"categories":888},[],{"categories":890},[137],{"categories":892},[140],{"categories":894},[61],{"categories":896},[61],{"categories":898},[176],{"categories":900},[137],{"categories":902},[450],{"categories":904},[176],{"categories":906},[137],{"categories":908},[61],{"categories":910},[61],{"categories":912},[61],{"categories":914},[155],{"categories":916},[],{"categories":918},[140],{"categories":920},[137],{"categories":922},[176],{"categories":924},[137],{"categories":926},[186],{"categories":928},[176],{"categories":930},[137],{"categories":932},[155],{"categories":934},[],{"categories":936},[61],{"categories":938},[176],{"categories":940},[61],{"categories":942},[129],{"categories":944},[155],{"categories":946},[61],{"categories":948},[193],{"categories":950},[61],{"categories":952},[61],{"categories":954},[137],{"categories":956},[137],{"categories":958},[61],{"categories":960},[137],{"categories":962},[176],{"categories":964},[61],{"categories":966},[],{"categories":968},[],{"categories":970},[186],{"categories":972},[],{"categories":974},[129],{"categories":976},[450],{"categories":978},[],{"categories":980},[129],{"categories":982},[132],{"categories":984},[193],{"categories":986},[],{"categories":988},[132],{"categories":990},[],{"categories":992},[],{"categories":994},[],{"categories":996},[],{"categories":998},[],{"categories":1000},[61],{"categories":1002},[137],{"categories":1004},[450],{"categories":1006},[129],{"categories":1008},[61],{"categories":1010},[186],{"categories":1012},[140],{"categories":1014},[61],{"categories":1016},[193],{"categories":1018},[61],{"categories":1020},[61],{"categories":1022},[61],{"categories":1024},[61,129],{"categories":1026},[186],{"categories":1028},[186],{"categories":1030},[176],{"categories":1032},[61],{"categories":1034},[],{"categories":1036},[],{"categories":1038},[],{"categories":1040},[186],{"categories":1042},[179],{"categories":1044},[155],{"categories":1046},[176],{"categories":1048},[],{"categories":1050},[61],{"categories":1052},[61],{"categories":1054},[],{"categories":1056},[],{"categories":1058},[137],{"categories":1060},[61],{"categories":1062},[132],{"categories":1064},[],{"categories":1066},[129],{"categories":1068},[61],{"categories":1070},[129],{"categories":1072},[61],{"categories":1074},[186],{"categories":1076},[193],{"categories":1078},[61,176],{"categories":1080},[155],{"categories":1082},[176],{"categories":1084},[],{"categories":1086},[450],{"categories":1088},[176],{"categories":1090},[137],{"categories":1092},[],{"categories":1094},[],{"categories":1096},[],{"categories":1098},[],{"categories":1100},[186],{"categories":1102},[137],{"categories":1104},[137],{"categories":1106},[450],{"categories":1108},[61],{"categories":1110},[61],{"categories":1112},[61],{"categories":1114},[],{"categories":1116},[176],{"categories":1118},[],{"categories":1120},[],{"categories":1122},[137],{"categories":1124},[],{"categories":1126},[],{"categories":1128},[193],{"categories":1130},[193],{"categories":1132},[137],{"categories":1134},[],{"categories":1136},[61],{"categories":1138},[61],{"categories":1140},[186],{"categories":1142},[176],{"categories":1144},[176],{"categories":1146},[137],{"categories":1148},[129],{"categories":1150},[61],{"categories":1152},[176],{"categories":1154},[176],{"categories":1156},[137],{"categories":1158},[137],{"categories":1160},[61],{"categories":1162},[],{"categories":1164},[],{"categories":1166},[61],{"categories":1168},[137],{"categories":1170},[155],{"categories":1172},[186],{"categories":1174},[129],{"categories":1176},[61],{"categories":1178},[],{"categories":1180},[137],{"categories":1182},[137],{"categories":1184},[],{"categories":1186},[129],{"categories":1188},[61],{"categories":1190},[129],{"categories":1192},[129],{"categories":1194},[],{"categories":1196},[],{"categories":1198},[137],{"categories":1200},[137],{"categories":1202},[61],{"categories":1204},[61],{"categories":1206},[155],{"categories":1208},[179],{"categories":1210},[140],{"categories":1212},[155],{"categories":1214},[176],{"categories":1216},[],{"categories":1218},[155],{"categories":1220},[],{"categories":1222},[],{"categories":1224},[],{"categories":1226},[],{"categories":1228},[186],{"categories":1230},[179],{"categories":1232},[],{"categories":1234},[61],{"categories":1236},[61],{"categories":1238},[179],{"categories":1240},[186],{"categories":1242},[],{"categories":1244},[],{"categories":1246},[137],{"categories":1248},[155],{"categories":1250},[155],{"categories":1252},[137],{"categories":1254},[129],{"categories":1256},[61,450],{"categories":1258},[],{"categories":1260},[176],{"categories":1262},[129],{"categories":1264},[137],{"categories":1266},[176],{"categories":1268},[],{"categories":1270},[137],{"categories":1272},[137],{"categories":1274},[61],{"categories":1276},[193],{"categories":1278},[186],{"categories":1280},[176],{"categories":1282},[],{"categories":1284},[137],{"categories":1286},[61],{"categories":1288},[137],{"categories":1290},[137],{"categories":1292},[137],{"categories":1294},[193],{"categories":1296},[137],{"categories":1298},[61],{"categories":1300},[],{"categories":1302},[193],{"categories":1304},[155],{"categories":1306},[137],{"categories":1308},[],{"categories":1310},[],{"categories":1312},[61],{"categories":1314},[137],{"categories":1316},[155],{"categories":1318},[137],{"categories":1320},[],{"categories":1322},[],{"categories":1324},[],{"categories":1326},[137],{"categories":1328},[],{"categories":1330},[],{"categories":1332},[179],{"categories":1334},[61],{"categories":1336},[179],{"categories":1338},[155],{"categories":1340},[61],{"categories":1342},[61],{"categories":1344},[137],{"categories":1346},[61],{"categories":1348},[],{"categories":1350},[],{"categories":1352},[450],{"categories":1354},[],{"categories":1356},[],{"categories":1358},[129],{"categories":1360},[],{"categories":1362},[],{"categories":1364},[],{"categories":1366},[],{"categories":1368},[186],{"categories":1370},[155],{"categories":1372},[193],{"categories":1374},[132],{"categories":1376},[61],{"categories":1378},[61],{"categories":1380},[132],{"categories":1382},[],{"categories":1384},[176],{"categories":1386},[137],{"categories":1388},[132],{"categories":1390},[61],{"categories":1392},[61],{"categories":1394},[129],{"categories":1396},[],{"categories":1398},[129],{"categories":1400},[61],{"categories":1402},[193],{"categories":1404},[137],{"categories":1406},[155],{"categories":1408},[132],{"categories":1410},[61],{"categories":1412},[137],{"categories":1414},[],{"categories":1416},[61],{"categories":1418},[129],{"categories":1420},[61],{"categories":1422},[],{"categories":1424},[155],{"categories":1426},[61],{"categories":1428},[],{"categories":1430},[132],{"categories":1432},[61],{"categories":1434},[],{"categories":1436},[],{"categories":1438},[],{"categories":1440},[61],{"categories":1442},[],{"categories":1444},[450],{"categories":1446},[61],{"categories":1448},[],{"categories":1450},[61],{"categories":1452},[61],{"categories":1454},[61],{"categories":1456},[61,450],{"categories":1458},[61],{"categories":1460},[61],{"categories":1462},[176],{"categories":1464},[137],{"categories":1466},[],{"categories":1468},[137],{"categories":1470},[61],{"categories":1472},[61],{"categories":1474},[61],{"categories":1476},[129],{"categories":1478},[129],{"categories":1480},[186],{"categories":1482},[176],{"categories":1484},[137],{"categories":1486},[],{"categories":1488},[61],{"categories":1490},[155],{"categories":1492},[61],{"categories":1494},[132],{"categories":1496},[],{"categories":1498},[450],{"categories":1500},[176],{"categories":1502},[176],{"categories":1504},[137],{"categories":1506},[155],{"categories":1508},[137],{"categories":1510},[61],{"categories":1512},[],{"categories":1514},[61],{"categories":1516},[],{"categories":1518},[],{"categories":1520},[61],{"categories":1522},[61],{"categories":1524},[61],{"categories":1526},[137],{"categories":1528},[61],{"categories":1530},[],{"categories":1532},[179],{"categories":1534},[137],{"categories":1536},[],{"categories":1538},[],{"categories":1540},[61],{"categories":1542},[155],{"categories":1544},[],{"categories":1546},[176],{"categories":1548},[450],{"categories":1550},[155],{"categories":1552},[186],{"categories":1554},[186],{"categories":1556},[155],{"categories":1558},[155],{"categories":1560},[450],{"categories":1562},[],{"categories":1564},[155],{"categories":1566},[61],{"categories":1568},[129],{"categories":1570},[155],{"categories":1572},[],{"categories":1574},[179],{"categories":1576},[155],{"categories":1578},[186],{"categories":1580},[155],{"categories":1582},[450],{"categories":1584},[61],{"categories":1586},[61],{"categories":1588},[],{"categories":1590},[132],{"categories":1592},[],{"categories":1594},[],{"categories":1596},[61],{"categories":1598},[61],{"categories":1600},[61],{"categories":1602},[61],{"categories":1604},[],{"categories":1606},[179],{"categories":1608},[129],{"categories":1610},[],{"categories":1612},[61],{"categories":1614},[61],{"categories":1616},[450],{"categories":1618},[450],{"categories":1620},[],{"categories":1622},[137],{"categories":1624},[155],{"categories":1626},[155],{"categories":1628},[61],{"categories":1630},[137],{"categories":1632},[],{"categories":1634},[176],{"categories":1636},[61],{"categories":1638},[61],{"categories":1640},[],{"categories":1642},[],{"categories":1644},[450],{"categories":1646},[61],{"categories":1648},[186],{"categories":1650},[132],{"categories":1652},[61],{"categories":1654},[],{"categories":1656},[137],{"categories":1658},[129],{"categories":1660},[129],{"categories":1662},[],{"categories":1664},[61],{"categories":1666},[176],{"categories":1668},[137],{"categories":1670},[],{"categories":1672},[61],{"categories":1674},[61],{"categories":1676},[137],{"categories":1678},[],{"categories":1680},[137],{"categories":1682},[186],{"categories":1684},[],{"categories":1686},[61],{"categories":1688},[],{"categories":1690},[61],{"categories":1692},[],{"categories":1694},[61],{"categories":1696},[61],{"categories":1698},[],{"categories":1700},[61],{"categories":1702},[155],{"categories":1704},[61],{"categories":1706},[61],{"categories":1708},[129],{"categories":1710},[61],{"categories":1712},[155],{"categories":1714},[137],{"categories":1716},[],{"categories":1718},[61],{"categories":1720},[193],{"categories":1722},[],{"categories":1724},[],{"categories":1726},[],{"categories":1728},[129],{"categories":1730},[155],{"categories":1732},[137],{"categories":1734},[61],{"categories":1736},[176],{"categories":1738},[137],{"categories":1740},[],{"categories":1742},[137],{"categories":1744},[],{"categories":1746},[61],{"categories":1748},[137],{"categories":1750},[61],{"categories":1752},[],{"categories":1754},[61],{"categories":1756},[61],{"categories":1758},[155],{"categories":1760},[176],{"categories":1762},[137],{"categories":1764},[176],{"categories":1766},[132],{"categories":1768},[],{"categories":1770},[],{"categories":1772},[61],{"categories":1774},[129],{"categories":1776},[155],{"categories":1778},[],{"categories":1780},[],{"categories":1782},[186],{"categories":1784},[176],{"categories":1786},[],{"categories":1788},[61],{"categories":1790},[],{"categories":1792},[193],{"categories":1794},[61],{"categories":1796},[450],{"categories":1798},[186],{"categories":1800},[],{"categories":1802},[137],{"categories":1804},[61],{"categories":1806},[137],{"categories":1808},[137],{"categories":1810},[61],{"categories":1812},[],{"categories":1814},[129],{"categories":1816},[61],{"categories":1818},[132],{"categories":1820},[186],{"categories":1822},[176],{"categories":1824},[],{"categories":1826},[],{"categories":1828},[],{"categories":1830},[137],{"categories":1832},[176],{"categories":1834},[155],{"categories":1836},[61],{"categories":1838},[155],{"categories":1840},[176],{"categories":1842},[],{"categories":1844},[176],{"categories":1846},[155],{"categories":1848},[132],{"categories":1850},[61],{"categories":1852},[155],{"categories":1854},[193],{"categories":1856},[],{"categories":1858},[],{"categories":1860},[179],{"categories":1862},[61,186],{"categories":1864},[155],{"categories":1866},[61],{"categories":1868},[137],{"categories":1870},[137],{"categories":1872},[61],{"categories":1874},[],{"categories":1876},[186],{"categories":1878},[61],{"categories":1880},[179],{"categories":1882},[137],{"categories":1884},[193],{"categories":1886},[450],{"categories":1888},[],{"categories":1890},[129],{"categories":1892},[137],{"categories":1894},[137],{"categories":1896},[186],{"categories":1898},[61],{"categories":1900},[61],{"categories":1902},[],{"categories":1904},[],{"categories":1906},[],{"categories":1908},[450],{"categories":1910},[155],{"categories":1912},[61],{"categories":1914},[61],{"categories":1916},[61],{"categories":1918},[],{"categories":1920},[179],{"categories":1922},[132],{"categories":1924},[],{"categories":1926},[137],{"categories":1928},[450],{"categories":1930},[],{"categories":1932},[176],{"categories":1934},[176],{"categories":1936},[],{"categories":1938},[186],{"categories":1940},[176],{"categories":1942},[61],{"categories":1944},[],{"categories":1946},[155],{"categories":1948},[61],{"categories":1950},[176],{"categories":1952},[137],{"categories":1954},[155],{"categories":1956},[],{"categories":1958},[137],{"categories":1960},[176],{"categories":1962},[61],{"categories":1964},[],{"categories":1966},[61],{"categories":1968},[61],{"categories":1970},[450],{"categories":1972},[155],{"categories":1974},[179],{"categories":1976},[179],{"categories":1978},[],{"categories":1980},[],{"categories":1982},[],{"categories":1984},[137],{"categories":1986},[186],{"categories":1988},[186],{"categories":1990},[],{"categories":1992},[],{"categories":1994},[61],{"categories":1996},[],{"categories":1998},[137],{"categories":2000},[61],{"categories":2002},[],{"categories":2004},[61],{"categories":2006},[132],{"categories":2008},[61],{"categories":2010},[193],{"categories":2012},[137],{"categories":2014},[61],{"categories":2016},[186],{"categories":2018},[155],{"categories":2020},[137],{"categories":2022},[],{"categories":2024},[155],{"categories":2026},[137],{"categories":2028},[137],{"categories":2030},[],{"categories":2032},[132],{"categories":2034},[137],{"categories":2036},[],{"categories":2038},[61],{"categories":2040},[129],{"categories":2042},[155],{"categories":2044},[450],{"categories":2046},[137],{"categories":2048},[137],{"categories":2050},[129],{"categories":2052},[61],{"categories":2054},[],{"categories":2056},[],{"categories":2058},[176],{"categories":2060},[61,132],{"categories":2062},[],{"categories":2064},[129],{"categories":2066},[179],{"categories":2068},[61],{"categories":2070},[186],{"categories":2072},[61],{"categories":2074},[137],{"categories":2076},[61],{"categories":2078},[61],{"categories":2080},[155],{"categories":2082},[137],{"categories":2084},[],{"categories":2086},[],{"categories":2088},[137],{"categories":2090},[61],{"categories":2092},[450],{"categories":2094},[],{"categories":2096},[61],{"categories":2098},[137],{"categories":2100},[],{"categories":2102},[61],{"categories":2104},[193],{"categories":2106},[179],{"categories":2108},[137],{"categories":2110},[61],{"categories":2112},[450],{"categories":2114},[],{"categories":2116},[61],{"categories":2118},[193],{"categories":2120},[176],{"categories":2122},[61],{"categories":2124},[],{"categories":2126},[193],{"categories":2128},[155],{"categories":2130},[61],{"categories":2132},[61],{"categories":2134},[129],{"categories":2136},[],{"categories":2138},[],{"categories":2140},[176],{"categories":2142},[61],{"categories":2144},[179],{"categories":2146},[193],{"categories":2148},[193],{"categories":2150},[155],{"categories":2152},[],{"categories":2154},[],{"categories":2156},[61],{"categories":2158},[],{"categories":2160},[61,186],{"categories":2162},[155],{"categories":2164},[137],{"categories":2166},[186],{"categories":2168},[61],{"categories":2170},[129],{"categories":2172},[],{"categories":2174},[],{"categories":2176},[129],{"categories":2178},[193],{"categories":2180},[61],{"categories":2182},[],{"categories":2184},[176,61],{"categories":2186},[450],{"categories":2188},[129],{"categories":2190},[],{"categories":2192},[132],{"categories":2194},[132],{"categories":2196},[61],{"categories":2198},[186],{"categories":2200},[137],{"categories":2202},[155],{"categories":2204},[193],{"categories":2206},[176],{"categories":2208},[61],{"categories":2210},[61],{"categories":2212},[61],{"categories":2214},[129],{"categories":2216},[61],{"categories":2218},[137],{"categories":2220},[155],{"categories":2222},[],{"categories":2224},[],{"categories":2226},[179],{"categories":2228},[186],{"categories":2230},[61],{"categories":2232},[176],{"categories":2234},[179],{"categories":2236},[61],{"categories":2238},[61],{"categories":2240},[137],{"categories":2242},[137],{"categories":2244},[61,132],{"categories":2246},[],{"categories":2248},[176],{"categories":2250},[],{"categories":2252},[61],{"categories":2254},[155],{"categories":2256},[129],{"categories":2258},[129],{"categories":2260},[137],{"categories":2262},[61],{"categories":2264},[132],{"categories":2266},[186],{"categories":2268},[193],{"categories":2270},[],{"categories":2272},[155],{"categories":2274},[61],{"categories":2276},[61],{"categories":2278},[155],{"categories":2280},[186],{"categories":2282},[61],{"categories":2284},[137],{"categories":2286},[155],{"categories":2288},[61],{"categories":2290},[176],{"categories":2292},[61],{"categories":2294},[61],{"categories":2296},[450],{"categories":2298},[140],{"categories":2300},[137],{"categories":2302},[61],{"categories":2304},[155],{"categories":2306},[137],{"categories":2308},[193],{"categories":2310},[61],{"categories":2312},[],{"categories":2314},[61],{"categories":2316},[],{"categories":2318},[],{"categories":2320},[],{"categories":2322},[132],{"categories":2324},[61],{"categories":2326},[137],{"categories":2328},[155],{"categories":2330},[155],{"categories":2332},[155],{"categories":2334},[155],{"categories":2336},[],{"categories":2338},[129],{"categories":2340},[137],{"categories":2342},[155],{"categories":2344},[129],{"categories":2346},[137],{"categories":2348},[61],{"categories":2350},[61,137],{"categories":2352},[137],{"categories":2354},[450],{"categories":2356},[155],{"categories":2358},[155],{"categories":2360},[137],{"categories":2362},[61],{"categories":2364},[],{"categories":2366},[155],{"categories":2368},[193],{"categories":2370},[129],{"categories":2372},[61],{"categories":2374},[61],{"categories":2376},[],{"categories":2378},[186],{"categories":2380},[],{"categories":2382},[129],{"categories":2384},[137],{"categories":2386},[155],{"categories":2388},[61],{"categories":2390},[155],{"categories":2392},[129],{"categories":2394},[155],{"categories":2396},[155],{"categories":2398},[],{"categories":2400},[132],{"categories":2402},[137],{"categories":2404},[155],{"categories":2406},[155],{"categories":2408},[155],{"categories":2410},[155],{"categories":2412},[155],{"categories":2414},[155],{"categories":2416},[155],{"categories":2418},[155],{"categories":2420},[155],{"categories":2422},[155],{"categories":2424},[179],{"categories":2426},[129],{"categories":2428},[61],{"categories":2430},[61],{"categories":2432},[],{"categories":2434},[61,129],{"categories":2436},[],{"categories":2438},[137],{"categories":2440},[155],{"categories":2442},[137],{"categories":2444},[61],{"categories":2446},[61],{"categories":2448},[61],{"categories":2450},[61],{"categories":2452},[61],{"categories":2454},[137],{"categories":2456},[132],{"categories":2458},[176],{"categories":2460},[155],{"categories":2462},[61],{"categories":2464},[],{"categories":2466},[],{"categories":2468},[137],{"categories":2470},[176],{"categories":2472},[61],{"categories":2474},[],{"categories":2476},[],{"categories":2478},[193],{"categories":2480},[61],{"categories":2482},[],{"categories":2484},[],{"categories":2486},[129],{"categories":2488},[132],{"categories":2490},[61],{"categories":2492},[132],{"categories":2494},[176],{"categories":2496},[],{"categories":2498},[155],{"categories":2500},[],{"categories":2502},[176],{"categories":2504},[61],{"categories":2506},[193],{"categories":2508},[],{"categories":2510},[193],{"categories":2512},[],{"categories":2514},[],{"categories":2516},[137],{"categories":2518},[],{"categories":2520},[132],{"categories":2522},[129],{"categories":2524},[176],{"categories":2526},[186],{"categories":2528},[],{"categories":2530},[],{"categories":2532},[61],{"categories":2534},[129],{"categories":2536},[193],{"categories":2538},[],{"categories":2540},[137],{"categories":2542},[137],{"categories":2544},[155],{"categories":2546},[61],{"categories":2548},[137],{"categories":2550},[61],{"categories":2552},[137],{"categories":2554},[61],{"categories":2556},[140],{"categories":2558},[155],{"categories":2560},[],{"categories":2562},[193],{"categories":2564},[186],{"categories":2566},[137],{"categories":2568},[],{"categories":2570},[61],{"categories":2572},[137],{"categories":2574},[132],{"categories":2576},[129],{"categories":2578},[61],{"categories":2580},[176],{"categories":2582},[186],{"categories":2584},[186],{"categories":2586},[61],{"categories":2588},[179],{"categories":2590},[61],{"categories":2592},[137],{"categories":2594},[132],{"categories":2596},[137],{"categories":2598},[61],{"categories":2600},[61],{"categories":2602},[137],{"categories":2604},[155],{"categories":2606},[],{"categories":2608},[129],{"categories":2610},[61],{"categories":2612},[137],{"categories":2614},[61],{"categories":2616},[61],{"categories":2618},[],{"categories":2620},[176],{"categories":2622},[132],{"categories":2624},[155],{"categories":2626},[61],{"categories":2628},[61],{"categories":2630},[176],{"categories":2632},[193],{"categories":2634},[179],{"categories":2636},[61],{"categories":2638},[155],{"categories":2640},[61],{"categories":2642},[137],{"categories":2644},[450],{"categories":2646},[61],{"categories":2648},[137],{"categories":2650},[179],{"categories":2652},[],{"categories":2654},[137],{"categories":2656},[186],{"categories":2658},[176],{"categories":2660},[61],{"categories":2662},[129],{"categories":2664},[132],{"categories":2666},[186],{"categories":2668},[],{"categories":2670},[137],{"categories":2672},[61],{"categories":2674},[],{"categories":2676},[155],{"categories":2678},[],{"categories":2680},[155],{"categories":2682},[61],{"categories":2684},[137],{"categories":2686},[137],{"categories":2688},[137],{"categories":2690},[],{"categories":2692},[],{"categories":2694},[61],{"categories":2696},[61],{"categories":2698},[],{"categories":2700},[176],{"categories":2702},[137],{"categories":2704},[193],{"categories":2706},[129],{"categories":2708},[],{"categories":2710},[],{"categories":2712},[155],{"categories":2714},[186],{"categories":2716},[61],{"categories":2718},[61],{"categories":2720},[61],{"categories":2722},[186],{"categories":2724},[155],{"categories":2726},[176],{"categories":2728},[61],{"categories":2730},[61],{"categories":2732},[61],{"categories":2734},[155],{"categories":2736},[61],{"categories":2738},[155],{"categories":2740},[137],{"categories":2742},[137],{"categories":2744},[186],{"categories":2746},[137],{"categories":2748},[61],{"categories":2750},[186],{"categories":2752},[176],{"categories":2754},[],{"categories":2756},[137],{"categories":2758},[],{"categories":2760},[],{"categories":2762},[],{"categories":2764},[132],{"categories":2766},[61],{"categories":2768},[137],{"categories":2770},[129],{"categories":2772},[137],{"categories":2774},[193],{"categories":2776},[],{"categories":2778},[137],{"categories":2780},[],{"categories":2782},[129],{"categories":2784},[137],{"categories":2786},[],{"categories":2788},[137],{"categories":2790},[61],{"categories":2792},[155],{"categories":2794},[61],{"categories":2796},[137],{"categories":2798},[155],{"categories":2800},[137],{"categories":2802},[186],{"categories":2804},[176],{"categories":2806},[129],{"categories":2808},[],{"categories":2810},[137],{"categories":2812},[176],{"categories":2814},[450],{"categories":2816},[155],{"categories":2818},[61],{"categories":2820},[176],{"categories":2822},[129],{"categories":2824},[],{"categories":2826},[137],{"categories":2828},[137],{"categories":2830},[61],{"categories":2832},[],{"categories":2834},[137],{"categories":2836},[140],{"categories":2838},[155],{"categories":2840},[137],{"categories":2842},[132],{"categories":2844},[],{"categories":2846},[61],{"categories":2848},[140],{"categories":2850},[61],{"categories":2852},[137],{"categories":2854},[155],{"categories":2856},[129],{"categories":2858},[450],{"categories":2860},[61],{"categories":2862},[61],{"categories":2864},[61],{"categories":2866},[155],{"categories":2868},[132],{"categories":2870},[61],{"categories":2872},[176],{"categories":2874},[155],{"categories":2876},[450],{"categories":2878},[61],{"categories":2880},[],{"categories":2882},[],{"categories":2884},[450],{"categories":2886},[179],{"categories":2888},[137],{"categories":2890},[137],{"categories":2892},[155],{"categories":2894},[61],{"categories":2896},[129],{"categories":2898},[176],{"categories":2900},[137],{"categories":2902},[61],{"categories":2904},[193],{"categories":2906},[61],{"categories":2908},[137],{"categories":2910},[],{"categories":2912},[61],{"categories":2914},[61],{"categories":2916},[155],{"categories":2918},[129],{"categories":2920},[],{"categories":2922},[61],{"categories":2924},[61],{"categories":2926},[186],{"categories":2928},[176],{"categories":2930},[61,137],{"categories":2932},[193,132],{"categories":2934},[61],{"categories":2936},[],{"categories":2938},[137],{"categories":2940},[],{"categories":2942},[186],{"categories":2944},[61],{"categories":2946},[155],{"categories":2948},[],{"categories":2950},[137],{"categories":2952},[],{"categories":2954},[176],{"categories":2956},[137],{"categories":2958},[129],{"categories":2960},[137],{"categories":2962},[61],{"categories":2964},[450],{"categories":2966},[193],{"categories":2968},[132],{"categories":2970},[132],{"categories":2972},[129],{"categories":2974},[129],{"categories":2976},[61],{"categories":2978},[137],{"categories":2980},[61],{"categories":2982},[61],{"categories":2984},[129],{"categories":2986},[61],{"categories":2988},[193],{"categories":2990},[155],{"categories":2992},[61],{"categories":2994},[137],{"categories":2996},[61],{"categories":2998},[],{"categories":3000},[186],{"categories":3002},[],{"categories":3004},[137],{"categories":3006},[129],{"categories":3008},[],{"categories":3010},[450],{"categories":3012},[61],{"categories":3014},[],{"categories":3016},[155],{"categories":3018},[137],{"categories":3020},[186],{"categories":3022},[61],{"categories":3024},[137],{"categories":3026},[186],{"categories":3028},[137],{"categories":3030},[155],{"categories":3032},[129],{"categories":3034},[155],{"categories":3036},[186],{"categories":3038},[61],{"categories":3040},[176],{"categories":3042},[61],{"categories":3044},[61],{"categories":3046},[61],{"categories":3048},[61],{"categories":3050},[137],{"categories":3052},[61],{"categories":3054},[137],{"categories":3056},[61],{"categories":3058},[129],{"categories":3060},[61],{"categories":3062},[137],{"categories":3064},[176],{"categories":3066},[129],{"categories":3068},[137],{"categories":3070},[176],{"categories":3072},[],{"categories":3074},[61],{"categories":3076},[61],{"categories":3078},[186],{"categories":3080},[],{"categories":3082},[137],{"categories":3084},[193],{"categories":3086},[61],{"categories":3088},[155],{"categories":3090},[193],{"categories":3092},[137],{"categories":3094},[132],{"categories":3096},[132],{"categories":3098},[61],{"categories":3100},[129],{"categories":3102},[],{"categories":3104},[61],{"categories":3106},[],{"categories":3108},[129],{"categories":3110},[61],{"categories":3112},[137],{"categories":3114},[137],{"categories":3116},[],{"categories":3118},[186],{"categories":3120},[186],{"categories":3122},[193],{"categories":3124},[176],{"categories":3126},[],{"categories":3128},[61],{"categories":3130},[129],{"categories":3132},[61],{"categories":3134},[186],{"categories":3136},[129],{"categories":3138},[155],{"categories":3140},[155],{"categories":3142},[],{"categories":3144},[155],{"categories":3146},[137],{"categories":3148},[176],{"categories":3150},[179],{"categories":3152},[61],{"categories":3154},[],{"categories":3156},[155],{"categories":3158},[186],{"categories":3160},[132],{"categories":3162},[61],{"categories":3164},[129],{"categories":3166},[450],{"categories":3168},[129],{"categories":3170},[],{"categories":3172},[],{"categories":3174},[155],{"categories":3176},[],{"categories":3178},[137],{"categories":3180},[137],{"categories":3182},[137],{"categories":3184},[],{"categories":3186},[61],{"categories":3188},[],{"categories":3190},[155],{"categories":3192},[129],{"categories":3194},[176],{"categories":3196},[61],{"categories":3198},[155],{"categories":3200},[155],{"categories":3202},[],{"categories":3204},[155],{"categories":3206},[129],{"categories":3208},[61],{"categories":3210},[],{"categories":3212},[137],{"categories":3214},[137],{"categories":3216},[129],{"categories":3218},[],{"categories":3220},[],{"categories":3222},[],{"categories":3224},[176],{"categories":3226},[137],{"categories":3228},[61],{"categories":3230},[],{"categories":3232},[],{"categories":3234},[],{"categories":3236},[176],{"categories":3238},[],{"categories":3240},[129],{"categories":3242},[],{"categories":3244},[],{"categories":3246},[176],{"categories":3248},[61],{"categories":3250},[155],{"categories":3252},[],{"categories":3254},[193],{"categories":3256},[155],{"categories":3258},[193],{"categories":3260},[61],{"categories":3262},[],{"categories":3264},[],{"categories":3266},[137],{"categories":3268},[],{"categories":3270},[],{"categories":3272},[137],{"categories":3274},[61],{"categories":3276},[],{"categories":3278},[137],{"categories":3280},[155],{"categories":3282},[193],{"categories":3284},[179],{"categories":3286},[137],{"categories":3288},[137],{"categories":3290},[],{"categories":3292},[],{"categories":3294},[],{"categories":3296},[155],{"categories":3298},[],{"categories":3300},[],{"categories":3302},[176],{"categories":3304},[129],{"categories":3306},[],{"categories":3308},[132],{"categories":3310},[193],{"categories":3312},[61],{"categories":3314},[186],{"categories":3316},[129],{"categories":3318},[179],{"categories":3320},[132],{"categories":3322},[186],{"categories":3324},[],{"categories":3326},[],{"categories":3328},[137],{"categories":3330},[129],{"categories":3332},[176],{"categories":3334},[129],{"categories":3336},[137],{"categories":3338},[450],{"categories":3340},[137],{"categories":3342},[],{"categories":3344},[61],{"categories":3346},[155],{"categories":3348},[186],{"categories":3350},[],{"categories":3352},[176],{"categories":3354},[155],{"categories":3356},[129],{"categories":3358},[137],{"categories":3360},[61],{"categories":3362},[132],{"categories":3364},[137,450],{"categories":3366},[137],{"categories":3368},[186],{"categories":3370},[61],{"categories":3372},[179],{"categories":3374},[193],{"categories":3376},[137],{"categories":3378},[],{"categories":3380},[137],{"categories":3382},[61],{"categories":3384},[132],{"categories":3386},[],{"categories":3388},[],{"categories":3390},[61],{"categories":3392},[179],{"categories":3394},[61],{"categories":3396},[],{"categories":3398},[155],{"categories":3400},[],{"categories":3402},[155],{"categories":3404},[186],{"categories":3406},[137],{"categories":3408},[61],{"categories":3410},[193],{"categories":3412},[186],{"categories":3414},[],{"categories":3416},[155],{"categories":3418},[61],{"categories":3420},[],{"categories":3422},[61],{"categories":3424},[137],{"categories":3426},[61],{"categories":3428},[137],{"categories":3430},[61],{"categories":3432},[61],{"categories":3434},[61],{"categories":3436},[61],{"categories":3438},[132],{"categories":3440},[],{"categories":3442},[140],{"categories":3444},[155],{"categories":3446},[61],{"categories":3448},[],{"categories":3450},[186],{"categories":3452},[61],{"categories":3454},[61],{"categories":3456},[137],{"categories":3458},[155],{"categories":3460},[61],{"categories":3462},[61],{"categories":3464},[132],{"categories":3466},[137],{"categories":3468},[176],{"categories":3470},[],{"categories":3472},[179],{"categories":3474},[61],{"categories":3476},[],{"categories":3478},[155],{"categories":3480},[193],{"categories":3482},[],{"categories":3484},[],{"categories":3486},[155],{"categories":3488},[155],{"categories":3490},[193],{"categories":3492},[129],{"categories":3494},[137],{"categories":3496},[137],{"categories":3498},[61],{"categories":3500},[132],{"categories":3502},[],{"categories":3504},[],{"categories":3506},[155],{"categories":3508},[179],{"categories":3510},[186],{"categories":3512},[137],{"categories":3514},[176],{"categories":3516},[179],{"categories":3518},[179],{"categories":3520},[],{"categories":3522},[155],{"categories":3524},[61],{"categories":3526},[61],{"categories":3528},[186],{"categories":3530},[],{"categories":3532},[155],{"categories":3534},[155],{"categories":3536},[155],{"categories":3538},[],{"categories":3540},[137],{"categories":3542},[61],{"categories":3544},[],{"categories":3546},[129],{"categories":3548},[132],{"categories":3550},[],{"categories":3552},[61],{"categories":3554},[61],{"categories":3556},[],{"categories":3558},[186],{"categories":3560},[],{"categories":3562},[],{"categories":3564},[],{"categories":3566},[],{"categories":3568},[61],{"categories":3570},[155],{"categories":3572},[],{"categories":3574},[],{"categories":3576},[61],{"categories":3578},[61],{"categories":3580},[61],{"categories":3582},[179],{"categories":3584},[61],{"categories":3586},[179],{"categories":3588},[],{"categories":3590},[179],{"categories":3592},[179],{"categories":3594},[450],{"categories":3596},[137],{"categories":3598},[186],{"categories":3600},[],{"categories":3602},[],{"categories":3604},[179],{"categories":3606},[186],{"categories":3608},[186],{"categories":3610},[186],{"categories":3612},[],{"categories":3614},[129],{"categories":3616},[186],{"categories":3618},[186],{"categories":3620},[129],{"categories":3622},[186],{"categories":3624},[132],{"categories":3626},[186],{"categories":3628},[186],{"categories":3630},[186],{"categories":3632},[179],{"categories":3634},[155],{"categories":3636},[155],{"categories":3638},[61],{"categories":3640},[186],{"categories":3642},[179],{"categories":3644},[450],{"categories":3646},[179],{"categories":3648},[179],{"categories":3650},[179],{"categories":3652},[],{"categories":3654},[132],{"categories":3656},[],{"categories":3658},[450],{"categories":3660},[186],{"categories":3662},[186],{"categories":3664},[186],{"categories":3666},[137],{"categories":3668},[155,132],{"categories":3670},[179],{"categories":3672},[],{"categories":3674},[],{"categories":3676},[179],{"categories":3678},[],{"categories":3680},[179],{"categories":3682},[155],{"categories":3684},[137],{"categories":3686},[],{"categories":3688},[186],{"categories":3690},[61],{"categories":3692},[176],{"categories":3694},[],{"categories":3696},[61],{"categories":3698},[],{"categories":3700},[155],{"categories":3702},[129],{"categories":3704},[179],{"categories":3706},[],{"categories":3708},[186],{"categories":3710},[155],[3712,3784,3873,3962],{"id":3713,"title":3714,"ai":3715,"body":3720,"categories":3760,"created_at":62,"date_modified":62,"description":54,"extension":63,"faq":62,"featured":64,"kicker_label":62,"meta":3761,"navigation":108,"path":3771,"published_at":3772,"question":62,"scraped_at":3773,"seo":3774,"sitemap":3775,"source_id":3776,"source_name":3777,"source_type":116,"source_url":3778,"stem":3779,"tags":3780,"thumbnail_url":62,"tldr":3781,"tweet":62,"unknown_tags":3782,"__hash__":3783},"summaries\u002Fsummaries\u002F1b682c7e4ee45c46-637mb-llm-runs-offline-on-base-macbook-air-works-s-summary.md","637MB LLM Runs Offline on Base MacBook Air, Works Surprisingly Well",{"provider":7,"model":8,"input_tokens":3716,"output_tokens":3717,"processing_time_ms":3718,"cost_usd":3719},5208,1356,14310,0.00121275,{"type":14,"value":3721,"toc":3755},[3722,3726,3741,3745,3748,3752],[17,3723,3725],{"id":3724},"effortless-local-setup-delivers-instant-offline-inference","Effortless Local Setup Delivers Instant, Offline Inference",[22,3727,3728,3729,3732,3733,3736,3737,3740],{},"Install Ollama with ",[46,3730,3731],{},"brew install ollama",", start the server via ",[46,3734,3735],{},"ollama serve",", and load TinyLlama—a 700MB model based on Llama 2—with ",[46,3738,3739],{},"ollama run tinyllama",". This three-command process skips Docker, Python environments, API keys, and accounts, downloading the model once for subsequent instant loads. On a base MacBook Air (no GPU or cooling upgrades), responses stream without latency, spinners, or internet—working in tunnels or planes with zero data telemetry, rate limits, or quotas. Tokens appear as fast as local typing, shifting AI from remote servers to a self-contained file.",[17,3742,3744],{"id":3743},"handles-practical-tasks-like-a-junior-dev-fails-on-complexity","Handles Practical Tasks Like a Junior Dev, Fails on Complexity",[22,3746,3747],{},"TinyLlama generates a fully functional Node.js Express server with routes, middleware, error handling, and comments—copy-paste runnable without edits. In casual conversations, it explains REST vs. GraphQL differences naturally, matching a coworker's tone and gently correcting user errors without robotic disclaimers. Limits emerge in long contexts (forgets details), multi-step reasoning (loses track of ideas), and hallucinations (invents nonexistent libraries). Failures resemble a junior developer's gaps—coherent but bounded—not random nonsense, making it viable for autocomplete, email rewrites, error explanations, and summaries.",[17,3749,3751],{"id":3750},"lowers-ai-floor-for-privacy-accessibility-and-everyday-use","Lowers AI Floor for Privacy, Accessibility, and Everyday Use",[22,3753,3754],{},"This setup democratizes AI: embed models in apps for offline assistants, enable learning in low-connectivity areas, process sensitive data without third-party uploads, and eliminate per-token costs. For the 'long tail' of routine tasks, small local models suffice, decoupling utility from massive scale, GPUs, and cloud bills. Frontier models still dominate complex reasoning, but the baseline shifts from paid APIs to free laptop files—challenging 'bigger is always better' narratives. Next steps include editor-integrated coding aids, personal fine-tunes on notes, multi-agent small-model collaborations, and offline RAG over documents.",{"title":54,"searchDepth":55,"depth":55,"links":3756},[3757,3758,3759],{"id":3724,"depth":55,"text":3725},{"id":3743,"depth":55,"text":3744},{"id":3750,"depth":55,"text":3751},[61],{"content_references":3762,"triage":3769},[3763,3766,3767],{"type":78,"title":3764,"context":3765},"TinyLlama","recommended",{"type":78,"title":79,"context":3765},{"type":91,"title":3768,"context":72},"Llama 2",{"relevance":104,"novelty":105,"quality":104,"actionability":104,"composite":106,"reasoning":3770},"Category: AI & LLMs. The article discusses the practical application of a lightweight LLM that can run offline, addressing the audience's pain point of integrating AI into their products without heavy infrastructure. It provides a clear setup process and examples of practical tasks the model can handle, making it actionable for developers.","\u002Fsummaries\u002F1b682c7e4ee45c46-637mb-llm-runs-offline-on-base-macbook-air-works-s-summary","2026-05-05 18:01:01","2026-05-06 16:13:47",{"title":3714,"description":54},{"loc":3771},"1b682c7e4ee45c46","Towards AI","https:\u002F\u002Fpub.towardsai.net\u002Fi-ran-a-637mb-llm-on-my-base-macbook-air-and-now-im-questioning-everything-cd78287d0ccc?source=rss----98111c9905da---4","summaries\u002F1b682c7e4ee45c46-637mb-llm-runs-offline-on-base-macbook-air-works-s-summary",[120,122,121],"TinyLlama, a 637MB open-source LLM, runs instantly on a stock MacBook Air via Ollama—no internet, GPU, or API needed—handling Node.js servers and casual chats effectively, lowering the bar for useful local AI.",[],"q08Qvpflcgj-8E3EIjojpd_j_dc9AsoFnv5ZNE-FrQc",{"id":3785,"title":3786,"ai":3787,"body":3792,"categories":3830,"created_at":62,"date_modified":62,"description":54,"extension":63,"faq":62,"featured":64,"kicker_label":62,"meta":3831,"navigation":108,"path":3861,"published_at":62,"question":62,"scraped_at":3862,"seo":3863,"sitemap":3864,"source_id":3865,"source_name":3866,"source_type":116,"source_url":3867,"stem":3868,"tags":3869,"thumbnail_url":62,"tldr":3870,"tweet":62,"unknown_tags":3871,"__hash__":3872},"summaries\u002Fsummaries\u002Fd831938b547e2834-sglang-fast-llm-serving-on-400k-gpus-summary.md","SGLang: Fast LLM Serving on 400k+ GPUs",{"provider":7,"model":8,"input_tokens":3788,"output_tokens":3789,"processing_time_ms":3790,"cost_usd":3791},6968,2130,10248,0.00195175,{"type":14,"value":3793,"toc":3825},[3794,3798,3801,3805,3814,3818],[17,3795,3797],{"id":3796},"delivering-production-grade-llm-inference","Delivering Production-Grade LLM Inference",[22,3799,3800],{},"SGLang serves large language models (LLMs) and multimodal models with low latency and high throughput across setups from one GPU to distributed clusters. It has 11,684 commits, active releases (49 total), and runs on PyPI with monthly downloads tracked. Benchmarks and performance details appear in release blogs like v0.2 (optimized for Llama3), v0.3, v0.4, large-scale expert parallelism, GB200 rack-scale, and GB300 long context. Use it to handle massive inference loads without performance drops in production.",[17,3802,3804],{"id":3803},"massive-adoption-drives-reliability","Massive Adoption Drives Reliability",[22,3806,3807,3808,3813],{},"Deployed at scale generating trillions of tokens daily, SGLang runs on over 400,000 GPUs globally as the de facto open-source inference standard. Trusted by xAI, AMD, NVIDIA, Intel, LinkedIn, Cursor, Oracle Cloud, Google Cloud, Microsoft Azure, AWS, and universities like MIT, UCLA, Stanford, UC Berkeley, Tsinghua. Hosted by non-profit LMSYS, it resolves issues quickly (badges show high closure rates, low open issues). Enterprises contact ",[3809,3810,3812],"a",{"href":3811},"mailto:sglang@lmsys.org","sglang@lmsys.org"," for scaled deployments or sponsorships; contributors get coding agent perks like Cursor or Claude Code.",[17,3815,3817],{"id":3816},"quick-setup-and-ecosystem-integration","Quick Setup and Ecosystem Integration",[22,3819,3820,3821,3824],{},"Start via PyPI (",[46,3822,3823],{},"pip install sglang","), with folders for benchmarks, docs, examples, Python code, Docker, tests, and kernels. Join Slack, weekly dev meetings, roadmap, or docs at docs.sglang.io. Draws from Guidance, vLLM, LightLLM, FlashInfer, Outlines, LMQL for design and code reuse. Repo includes dev containers, pre-commit hooks, and AMD 3rdparty support for broad hardware compatibility.",{"title":54,"searchDepth":55,"depth":55,"links":3826},[3827,3828,3829],{"id":3796,"depth":55,"text":3797},{"id":3803,"depth":55,"text":3804},{"id":3816,"depth":55,"text":3817},[61],{"content_references":3832,"triage":3859},[3833,3836,3838,3841,3844,3847,3850,3853,3856],{"type":78,"title":3834,"url":3835,"context":72},"Guidance","https:\u002F\u002Fgithub.com\u002Fguidance-ai\u002Fguidance",{"type":78,"title":88,"url":3837,"context":72},"https:\u002F\u002Fgithub.com\u002Fvllm-project\u002Fvllm",{"type":78,"title":3839,"url":3840,"context":72},"LightLLM","https:\u002F\u002Fgithub.com\u002FModelTC\u002Flightllm",{"type":78,"title":3842,"url":3843,"context":72},"FlashInfer","https:\u002F\u002Fgithub.com\u002Fflashinfer-ai\u002Fflashinfer",{"type":78,"title":3845,"url":3846,"context":72},"Outlines","https:\u002F\u002Fgithub.com\u002Foutlines-dev\u002Foutlines",{"type":78,"title":3848,"url":3849,"context":72},"LMQL","https:\u002F\u002Fgithub.com\u002Feth-sri\u002Flmql",{"type":91,"title":3851,"url":3852,"context":3765},"SGLang v0.2 blog","https:\u002F\u002Flmsys.org\u002Fblog\u002F2024-07-25-sglang-llama3\u002F",{"type":91,"title":3854,"url":3855,"context":3765},"SGLang v0.3 blog","https:\u002F\u002Flmsys.org\u002Fblog\u002F2024-09-04-sglang-v0-3\u002F",{"type":91,"title":3857,"url":3858,"context":3765},"SGLang v0.4 blog","https:\u002F\u002Flmsys.org\u002Fblog\u002F2024-12-04-sglang-v0-4\u002F",{"relevance":104,"novelty":105,"quality":104,"actionability":104,"composite":106,"reasoning":3860},"Category: AI & LLMs. The article discusses SGLang, an open-source tool for LLM inference, which directly addresses the audience's need for practical AI tooling. It provides specific details on setup and integration, making it actionable for developers looking to implement LLMs in production.","\u002Fsummaries\u002Fd831938b547e2834-sglang-fast-llm-serving-on-400k-gpus-summary","2026-04-16 03:06:56",{"title":3786,"description":54},{"loc":3861},"d831938b547e2834","__oneoff__","https:\u002F\u002Fgithub.com\u002Fsgl-project\u002Fsglang","summaries\u002Fd831938b547e2834-sglang-fast-llm-serving-on-400k-gpus-summary",[120,122,121],"SGLang enables low-latency, high-throughput LLM inference from single GPUs to clusters, powering trillions of daily tokens for xAI, NVIDIA, AMD, and 400,000+ GPUs worldwide.",[],"6IHR19L6zFlTb7B8EgD-yySDcCnhh0dJr8Ad451-MoA",{"id":3874,"title":3875,"ai":3876,"body":3881,"categories":3945,"created_at":62,"date_modified":62,"description":54,"extension":63,"faq":62,"featured":64,"kicker_label":62,"meta":3946,"navigation":108,"path":3952,"published_at":62,"question":62,"scraped_at":3953,"seo":3954,"sitemap":3955,"source_id":3956,"source_name":3866,"source_type":116,"source_url":3837,"stem":3957,"tags":3958,"thumbnail_url":62,"tldr":3959,"tweet":62,"unknown_tags":3960,"__hash__":3961},"summaries\u002Fsummaries\u002Fe8ba7172314e48e9-vllm-high-throughput-llm-serving-engine-summary.md","vLLM: High-Throughput LLM Serving Engine",{"provider":7,"model":8,"input_tokens":3877,"output_tokens":3878,"processing_time_ms":3879,"cost_usd":3880},10719,1226,7498,0.0027343,{"type":14,"value":3882,"toc":3940},[3883,3887,3890,3894,3897,3901],[17,3884,3886],{"id":3885},"key-capabilities-and-performance-focus","Key Capabilities and Performance Focus",[22,3888,3889],{},"vLLM serves as a high-throughput and memory-efficient inference and serving engine specifically for large language models (LLMs). It emphasizes practical deployment needs through optimized kernels, as seen in recent commits like W8A8 block linear refactors for FP8 operations and Helion kernel improvements using FakeTensorMode to cut GPU allocation during config computations. This enables faster serving in production by reducing memory overhead and boosting decode path efficiency via indexer metadata optimizations.",[17,3891,3893],{"id":3892},"repo-scale-and-community-momentum","Repo Scale and Community Momentum",[22,3895,3896],{},"With 75.8k stars and 15.4k forks, vLLM draws massive adoption among AI builders. It sustains high activity: 1.8k open issues, 2.3k pull requests, 272 branches, 140 tags, and 15,628 commits. Recent updates (as of Apr 9, 2026) include Docker enhancements adding fastsafetensors for NVIDIA builds, XPU test skips for EAGLE DP invariance, and multimodal fixes for nested tensor equality with length checks on lists\u002Ftuples. Funding via GitHub Sponsors and Open Collective supports ongoing development.",[17,3898,3900],{"id":3899},"development-structure-for-production-use","Development Structure for Production Use",[22,3902,3903,3904,3907,3908,3911,3912,3915,3916,3919,3920,3923,3924,3927,3928,3931,3932,3935,3936,3939],{},"The monorepo organizes for end-to-end workflows: ",[46,3905,3906],{},"benchmarks"," for performance testing, ",[46,3909,3910],{},"csrc"," for core C++\u002FCUDA implementations, ",[46,3913,3914],{},"docker"," for containerized deploys, ",[46,3917,3918],{},"docs"," and ",[46,3921,3922],{},"examples"," for quick starts, ",[46,3925,3926],{},"tests"," ensuring reliability (e.g., CI mypy fixes), and ",[46,3929,3930],{},"vllm"," core with multimodal and tool support like ",[46,3933,3934],{},"adjust_request"," for reasoning parsers. Tools like CMake integrate DeepGEMM for wheel builds, while ",[46,3937,3938],{},".github"," workflows enforce clang-format for C++\u002FCUDA style and pre-commit checks, making it reliable for small teams shipping LLM services without hype—just working throughput gains.",{"title":54,"searchDepth":55,"depth":55,"links":3941},[3942,3943,3944],{"id":3885,"depth":55,"text":3886},{"id":3892,"depth":55,"text":3893},{"id":3899,"depth":55,"text":3900},[61],{"content_references":3947,"triage":3948},[],{"relevance":3949,"novelty":104,"quality":104,"actionability":104,"composite":3950,"reasoning":3951},5,4.35,"Category: AI & LLMs. The article provides in-depth insights into vLLM, a high-throughput serving engine for LLMs, addressing practical deployment needs which is crucial for AI builders. It details specific optimizations and community engagement, making it actionable for developers looking to implement or contribute to LLM serving solutions.","\u002Fsummaries\u002Fe8ba7172314e48e9-vllm-high-throughput-llm-serving-engine-summary","2026-04-16 03:06:58",{"title":3875,"description":54},{"loc":3952},"e8ba7172314e48e9","summaries\u002Fe8ba7172314e48e9-vllm-high-throughput-llm-serving-engine-summary",[120,122,121],"vLLM provides high-throughput, memory-efficient inference and serving for LLMs; popular repo with 75.8k stars, 15.4k forks, active across benchmarks, docs, and kernels.",[],"WTuAM-yBeAomVNRCPCNmOXZTRuNv7iO0Y44UdofyG08",{"id":3963,"title":3964,"ai":3965,"body":3970,"categories":4001,"created_at":62,"date_modified":62,"description":54,"extension":63,"faq":62,"featured":64,"kicker_label":62,"meta":4002,"navigation":108,"path":4024,"published_at":4025,"question":62,"scraped_at":4026,"seo":4027,"sitemap":4028,"source_id":4029,"source_name":4030,"source_type":116,"source_url":4031,"stem":4032,"tags":4033,"thumbnail_url":62,"tldr":4034,"tweet":62,"unknown_tags":4035,"__hash__":4036},"summaries\u002Fsummaries\u002F0620e2900fa5d4a4-small-open-llms-replicate-claude-mythos-bug-hunts-summary.md","Small open LLMs replicate Claude Mythos bug hunts",{"provider":7,"model":8,"input_tokens":3966,"output_tokens":3967,"processing_time_ms":3968,"cost_usd":3969},5310,2704,20579,0.00239135,{"type":14,"value":3971,"toc":3996},[3972,3976,3979,3982,3986,3989,3993],[17,3973,3975],{"id":3974},"open-models-nail-high-profile-bugs-without-mythos","Open Models Nail High-Profile Bugs Without Mythos",[22,3977,3978],{},"Anthropic's Claude Mythos demoed autonomous bug discovery and exploitation, like the FreeBSD NFS memory bug (CVE-2026-4747), where it squeezes 1,000+ byte payloads into 304 bytes via 15 split network requests. But AISLE's tests show eight small open models—including GPT-OSS-20b (3.6B params, $0.11\u002FM tokens) and Kimi K2—all flagged this critical buffer overflow. They explained OS protections' irrelevance and proposed viable exploits; GPT-OSS-120b generated a near-real gadget chain, and Kimi K2 spotted auto-spreading attacks unmentioned by Anthropic. AISLE reported 15 OpenSSL and 5 curl vulns using similar setups. Vidoc paired GPT-5.4 and Claude Opus 4.6 with OpenCode agent to match these on Botan certificate flaws (logic gap caught 3\u002F3 runs) and wolfSSL crypto misreads, at under $30 per scanned file.",[22,3980,3981],{},"For fake vulns, like discarded user input in DB queries, small opens like Deepseek R1 and Kimi K2 succeeded every time, outperforming GPT-5.4 (0\u002F3) and some Claude versions (Sonnet 4.5 traced data wrong). Post-patch recognition lags: only GPT-OSS-120b reliably deemed fixed FreeBSD code safe; smaller models hallucinated issues.",[17,3983,3985],{"id":3984},"jagged-frontier-no-model-dominates-all-tasks","Jagged Frontier: No Model Dominates All Tasks",[22,3987,3988],{},"Capabilities spike unevenly. On OpenBSD integer overflow, GPT-OSS-120b rebuilt the full exploit chain and proposed the exact patch in one run, while Qwen3-32B (strong on FreeBSD) called code \"robust.\" Claude Opus 4.6 hit 3\u002F3, GPT-5.4 missed entirely. This \"jagged frontier\" means rankings flip per bug—pick models task-specifically, as no single frontier model wins universally.",[17,3990,3992],{"id":3991},"build-systems-not-model-worship-for-bug-hunting","Build Systems, Not Model Worship, for Bug Hunting",[22,3994,3995],{},"Mythos' edge shrinks to deployable exploits, but studies stress full pipelines: target selection, step-wise analysis, validation, prioritization, false-positive filtering. Small opens suffice for broad scanning—\"a thousand adequate detectives everywhere beat one brilliant guesser,\" per AISLE's Fort. Anthropic limits Mythos access via Project Glasswing (11 orgs) citing risks, but replications erode exclusivity claims. FT reports compute shortages delay wider release, fueling fears of hype. Use cheap opens + agents for production cybersecurity: scan widely, iterate workflows, and close the gap to proprietary models today.",{"title":54,"searchDepth":55,"depth":55,"links":3997},[3998,3999,4000],{"id":3974,"depth":55,"text":3975},{"id":3984,"depth":55,"text":3985},{"id":3991,"depth":55,"text":3992},[],{"content_references":4003,"triage":4021},[4004,4007,4012,4015,4017],{"type":78,"title":4005,"url":4006,"context":72},"Claude Mythos Preview","https:\u002F\u002Fthe-decoder.com\u002Ffrom-gpt-2-to-claude-mythos-the-return-of-ai-models-deemed-too-dangerous-to-release\u002F",{"type":91,"title":4008,"author":4009,"url":4010,"context":4011},"AI Cybersecurity After Mythos: The Jagged Frontier","Stanislav Fort","https:\u002F\u002Faisle.com\u002Fblog\u002Fai-cybersecurity-after-mythos-the-jagged-frontier","cited",{"type":91,"title":4013,"url":4014,"context":4011},"We Reproduced Anthropic's Mythos Findings with Public Models","https:\u002F\u002Fblog.vidocsecurity.com\u002Fblog\u002Fwe-reproduced-anthropics-mythos-findings-with-public-models",{"type":68,"title":4016,"context":4011},"Audit by UK's AI Security Institute",{"type":91,"title":4018,"publisher":4019,"url":4020,"context":4011},"Anthropic holding back model until compute ready","Financial Times","https:\u002F\u002Fwww.ft.com\u002Fcontent\u002Fc9f5b690-a10e-4c66-9245-017f8bfbc7b4?syn-25a6b1a6=1",{"relevance":105,"novelty":105,"quality":104,"actionability":55,"composite":4022,"reasoning":4023},3.05,"Category: AI & LLMs. The article discusses the performance of small open LLMs in cybersecurity bug detection, which is relevant to AI engineering. However, while it presents some interesting findings, it lacks concrete actionable steps for the audience to implement in their own AI-powered product development.","\u002Fsummaries\u002F0620e2900fa5d4a4-small-open-llms-replicate-claude-mythos-bug-hunts-summary","2026-04-18 08:48:05","2026-04-19 01:22:29",{"title":3964,"description":54},{"loc":4024},"0620e2900fa5d4a4","The Decoder","https:\u002F\u002Fthe-decoder.com\u002Fthe-myth-of-claude-mythos-crumbles-as-small-open-models-hunt-the-same-cybersecurity-bugs-anthropic-showcased\u002F","summaries\u002F0620e2900fa5d4a4-small-open-llms-replicate-claude-mythos-bug-hunts-summary",[120,122,121],"Small open models like 3.6B-param GPT-OSS-20b detect and exploit the same cybersecurity bugs as Anthropic's restricted Claude Mythos, proving pipelines—not model size—unlock capabilities.",[],"VBKlihfCzaQlnHh54O5H5Km4j4SoTWDZ3cLdtY20goQ"]