SGLang: Releases and Overview
LLM serving framework known for RadixAttention prefix caching and structured output. A common alternative to vLLM for serving.
Category: Inference engines and runtimes. Part of our engine and tool tracker.
At a Glance
| Item | Value |
|---|---|
| Repository | sgl-project/sglang |
| License | Apache-2.0 |
| Main language | Python |
| GitHub stars | 36,085 (as of 2026-09-17) |
| Latest release | v0.5.20 (2026-09-19) |
| Install / docs | official documentation |
The project describes itself as: “SGLang is a high-performance serving framework for large language models and multimodal models.”
Release History
Compiled by Local Model Watch from the project’s GitHub releases. Pre-releases are omitted. Where we wrote an article about a release, it is linked in the last column; smaller releases are tracked here only.
| Version | Released | Release notes | Our article |
|---|---|---|---|
| v0.5.20 | 2026-09-19 | GitHub | SGLang v0.5.20 Released: New Models and Optimizations |
| v0.5.19 | 2026-09-05 | GitHub | — |
| v0.5.18 | 2026-08-22 | GitHub | — |
| v0.5.17 | 2026-08-08 | GitHub | — |
| v0.5.16 | 2026-07-25 | GitHub | — |
| v0.5.15.post1 | 2026-07-14 | GitHub | — |
| v0.5.15 | 2026-07-11 | GitHub | — |
| v0.5.14 | 2026-06-27 | GitHub | — |
| v0.5.13 | 2026-06-13 | GitHub | — |
| v0.5.12.post1 | 2026-05-27 | GitHub | — |
| v0.5.12 | 2026-05-17 | GitHub | — |
| v0.5.11 | 2026-05-06 | GitHub | — |
| v0.5.10.post1 | 2026-04-09 | GitHub | — |
| v0.5.10 | 2026-04-06 | GitHub | — |
| v0.5.9 | 2026-02-24 | GitHub | — |
| v0.5.8 | 2026-01-24 | GitHub | — |
| gateway-v0.3.1 (Release Gateway-v0.3.1) | 2026-01-09 | GitHub | — |
| v0.5.7 | 2026-01-01 | GitHub | — |
| gateway-v0.3.0 (Release Gateway-v0.3.0) | 2025-12-25 | GitHub | — |
| gateway-v0.2.4 (Release Gateway-v0.2.4) | 2025-12-10 | GitHub | — |
| v0.5.6 | 2025-12-03 | GitHub | — |
| gateway-v0.2.3 (Release Gateway-v0.2.3) | 2025-11-17 | GitHub | — |
| gateway-v0.2.2 (Release Gateway-v0.2.2) | 2025-11-17 | GitHub | — |
| gateway-v0.2.1 (Release Gateway-v0.2.1) | 2025-11-17 | GitHub | — |
| gateway-v0.2.0 (Release Gateway-v0.2.0) | 2025-11-17 | GitHub | — |
| gateway-v0.1.9 (Release Gateway-v0.1.9) | 2025-11-17 | GitHub | — |
| gateway-v0.1.8 (Release Gateway-v0.1.8) | 2025-11-17 | GitHub | — |
| gateway-v0.1.7 (Release Gateway-v0.1.7) | 2025-11-17 | GitHub | — |
| gateway-v0.1.6 (Release Gateway-v0.1.6) | 2025-11-17 | GitHub | — |
| v0.5.5 | 2025-11-07 | GitHub | — |
| v0.5.4 | 2025-10-26 | GitHub | — |
| v0.5.3 | 2025-10-07 | GitHub | — |
| v0.5.2 | 2025-09-12 | GitHub | — |
| v0.5.1 | 2025-08-24 | GitHub | — |
| v0.4.10 | 2025-08-01 | GitHub | — |
| v0.4.8 | 2025-06-25 | GitHub | — |
| v0.4.7 | 2025-06-12 | GitHub | — |
| v0.4.6 | 2025-04-28 | GitHub | — |
| v0.4.5 | 2025-04-07 | GitHub | — |
| v0.4.4 | 2025-03-14 | GitHub | — |
| v0.4.3 | 2025-02-14 | GitHub | — |
| v0.4.1 | 2024-12-26 | GitHub | — |
| v0.4.0 | 2024-12-04 | GitHub | — |
| v0.3.6 | 2024-11-22 | GitHub | — |
| v0.3.4.post1 | 2024-10-22 | GitHub | — |
| v0.3.2 | 2024-10-03 | GitHub | — |
| v0.3.0 | 2024-09-19 | GitHub | — |
| v0.2.13 | 2024-09-19 | GitHub | — |
| v0.2.9 | 2024-08-02 | GitHub | — |
| v0.2.5 | 2024-07-27 | GitHub | — |
| v0.2.0 | 2024-07-26 | GitHub | — |
| v0.1.20 | 2024-07-14 | GitHub | — |
| v0.1.18 | 2024-07-04 | GitHub | — |
| v0.1.17 | 2024-06-08 | GitHub | — |
| v0.1.16 | 2024-05-14 | GitHub | — |
| v0.1.13 | 2024-03-11 | GitHub | — |
| v0.1.12 | 2024-02-11 | GitHub | — |
| v0.1.11 | 2024-02-03 | GitHub | — |
| v0.1.6 | 2024-01-21 | GitHub | — |
| v0.1.5 | 2024-01-18 | GitHub | — |
Articles on Local Model Watch
Last updated 2026-09-19 (JST). Facts above come from the GitHub API; the one-paragraph summary is written by the site’s editors.