{"slug": "sglang", "name": "SGLang", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 1, "commenters": 2, "warners": 0, "score": 1.248, "rising": 1.0, "first": "2026-08-23", "latest": "2026-08-29", "why": "", "why_is_quote": false, "has_verdict": false, "sentiment": {"recommend": 1, "neutral": 1, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0], "listed": false, "loved": [], "caveat": "", "short_quote": "", "icon": false, "domain": null, "github_repo": "github.com/sgl-project/sglang", "official_url": "https://github.com/sgl-project/sglang", "pricing": "", "aliases": ["SGLang"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 791896688, "item_id": 49493543, "url": "https://news.ycombinator.com/item?id=49493543", "by": "bugglebeetle", "date": "2026-08-29", "stance": "recommend", "quote": "was surprised how nice and painless things were", "excerpt": "I recently switched to using for some large volume inference with small, fine-tuned models and was surprised how nice and painless things were. vLLM seems to have a lot more gotchas and kludged together stuff once you get outside of anything straightforward.", "context": "Runs large-volume inference with small fine-tuned models", "use_case": "large volume inference with small fine-tuned models", "switched_from": "vLLM", "story": "vLLM v0.28.0"}]}], "caveats": [], "who": [{"by": "bugglebeetle", "context": "Runs large-volume inference with small fine-tuned models", "url": "https://news.ycombinator.com/item?id=49493543", "date": "2026-08-29"}, {"by": "TofuLover", "context": "runs an open-model API service", "url": "https://news.ycombinator.com/item?id=49409781", "date": "2026-08-23"}], "tags": [], "use_cases": ["large volume inference with small fine-tuned models", "serving open models"], "compared": [{"slug": "vllm", "name": "vLLM", "co": 3, "switched_from": 1, "switched_to": 0}], "makers": [{"id": 797702256, "item_id": 49856391, "url": "https://news.ycombinator.com/item?id=49856391", "by": "apejcic", "date": "2026-09-26", "stance": "neutral", "quote": "We serve several tenants on shared SGLang nodes", "excerpt": "Author here. We serve several tenants on shared SGLang nodes, and our p99 TTFT was bad while the median looked fine. The cause was head-of-line blocking in prefill. SGLang's scheduler lets only one request be mid-chunk at a time, and that request takes the whole chunked-prefill budget every round. So one cold 600K-token prompt held the prefill slot for about 105s. Everything queued behind it waited too, including req", "context": "serves several tenants on shared nodes", "use_case": "multi-tenant LLM serving", "switched_from": "", "story": "Prefill Concurrency in SGLang: Consistent TTFT Under Multi-Tenant Load"}], "threads": [{"url": "https://news.ycombinator.com/item?id=49856359", "title": "Prefill Concurrency in SGLang: Consistent TTFT Under Multi-Tenant Load", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49492067", "title": "vLLM v0.28.0", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49407507", "title": "I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {}, "2026-08": {"neutral": 1, "recommend": 1}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 791896688, "item_id": 49493543, "url": "https://news.ycombinator.com/item?id=49493543", "by": "bugglebeetle", "date": "2026-08-29", "stance": "recommend", "quote": "was surprised how nice and painless things were", "excerpt": "I recently switched to using for some large volume inference with small, fine-tuned models and was surprised how nice and painless things were. vLLM seems to have a lot more gotchas and kludged together stuff once you get outside of anything straightforward.", "context": "Runs large-volume inference with small fine-tuned models", "use_case": "large volume inference with small fine-tuned models", "switched_from": "vLLM", "story": "vLLM v0.28.0"}, {"id": 790556497, "item_id": 49409781, "url": "https://news.ycombinator.com/item?id=49409781", "by": "TofuLover", "date": "2026-08-23", "stance": "neutral", "quote": "We've been experimenting with SGLang though, and there's definitely some interesting optimisations we could do with it.", "excerpt": "These are great questions, thanks! I'll answer them in turn, in a list because I like lists. * Confidentiality: no logging, third party analytics, or anything like that. More details in our Privacy Poilicy [1]. Our hosting providers will have their own policies, but we're not running a super private service like Proton or similar. Might do some kind of secure tenancy in the future if there's demand. * Price: I think ", "context": "runs an open-model API service", "use_case": "serving open models", "switched_from": "", "story": "I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes"}]}