Tool · Inference runtime · SGLang Project
SGLang
SGLang is a high-performance serving framework for large language models and multimodal models.
- License
- PermissiveApache License 2.0
- Language
- Python
- Latest release
- 18 Sept 2026SGLang v0.5.20
- Measurements
- 0with this runtime
Relationships
No relationships recorded.
Releases & news
- SGLang v0.5.20713 PRs from 237 contributors.
- SGLang v0.5.19786 PRs from 214 contributors.
- SGLang v0.5.18710 PRs from 212 contributors.
- SGLang v0.5.17582 PRs from 194 contributors.
- SGLang v0.5.16574 PRs from 169 contributors.
- SGLang v0.5.15.post1v0.5.15.post1 includes a few patches, mostly for GLM 5.2
- SGLang v0.5.15GLM-5.2 NVFP4, tuned for production: We took time this cycle to tune GLM-5.2 NVFP4 on Blackwell for optimized production serving. It now runs at 500+ tok/s/user on 8x B300, 450 on 4x GB300 (bs=1). Run GLM-5.2 with our cookbook.
- SGLang v0.5.14New Model Support: GLM-5.2, LiquidAI LFM2.5, Kimi-K2.7-Code, Poolside Laguna-M.1, DiffusionGemma, Zyphra ZAYA1, MiMo-V2-ASR
- SGLang v0.5.13New Model Support:
- SGLang v0.5.12.post1v0.5.12.post1 is a stability patch on top of v0.5.12. It cherry-picks 12 fixes — primarily for DeepSeek V4 — onto the release branch.
- SGLang v0.5.12DeepSeek V4 support: Full inference path for DeepSeek-V4 (#23882), including:
Measured performance with this runtime
Throughput members and projects recorded, in tokens per secondHow fast the model writes its answer; about 10 tokens per second reads like comfortable typing..
No performance measurements recorded yet.
Reviews
Contributions are not open yet, so there is nothing here from members.
Sources & history
Sources
- GitHub (live source, 3 records, 19 Sept 2026)
External identifiers
- github sgl-project/sglang
Field history
- homepageUrl = "https://sglang.io" — GitHub (current)
- homepageUrl = "https://sglang.io" — GitHub
- homepageUrl = "https://sglang.io" — GitHub
- primaryLanguage = "Python" — GitHub (current)
- primaryLanguage = "Python" — GitHub
- primaryLanguage = "Python" — GitHub
- summary = "SGLang is a high-performance serving framework for large language models and multimodal models." — GitHub (current)
- summary = "SGLang is a high-performance serving framework for large language models and multimodal models." — GitHub
- summary = "SGLang is a high-performance serving framework for large language models and multimodal models." — GitHub