{"id":1250,"date":"2026-09-17T16:56:53","date_gmt":"2026-09-17T07:56:53","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/engine-sglang-en\/"},"modified":"2026-09-19T08:09:23","modified_gmt":"2026-09-18T23:09:23","slug":"engine-sglang-en","status":"publish","type":"page","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-sglang-en\/","title":{"rendered":"SGLang: Releases and Overview"},"content":{"rendered":"<p>LLM serving framework known for RadixAttention prefix caching and structured output. A common alternative to vLLM for serving.<\/p>\n<p><em>Category: Inference engines and runtimes. Part of our <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engines-en\/\">engine and tool tracker<\/a>.<\/em><\/p>\n<h2>At a Glance<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Item<\/th>\n<th>Value<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Repository<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\">sgl-project\/sglang<\/a><\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>Apache-2.0<\/td>\n<\/tr>\n<tr>\n<td>Main language<\/td>\n<td>Python<\/td>\n<\/tr>\n<tr>\n<td>GitHub stars<\/td>\n<td>36,085 (as of 2026-09-17)<\/td>\n<\/tr>\n<tr>\n<td>Latest release<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.20\">v0.5.20<\/a> (2026-09-19)<\/td>\n<\/tr>\n<tr>\n<td>Install \/ docs<\/td>\n<td><a href=\"https:\/\/docs.sglang.ai\/start\/install.html\">official documentation<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>The project describes itself as: \u201cSGLang is a high-performance serving framework for large language models and multimodal models.\u201d<\/p>\n<h2>Release History<\/h2>\n<p><em>Compiled by Local Model Watch from the project&#8217;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.<\/em><\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Version<\/th>\n<th>Released<\/th>\n<th>Release notes<\/th>\n<th>Our article<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>v0.5.20<\/td>\n<td>2026-09-19<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.20\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/19\/sglang-v0-5-20-released\/\">SGLang v0.5.20 Released: New Models and Optimizations<\/a><\/td>\n<\/tr>\n<tr>\n<td>v0.5.19<\/td>\n<td>2026-09-05<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.19\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.18<\/td>\n<td>2026-08-22<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.18\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.17<\/td>\n<td>2026-08-08<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.17\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.16<\/td>\n<td>2026-07-25<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.16\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.15.post1<\/td>\n<td>2026-07-14<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.15.post1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.15<\/td>\n<td>2026-07-11<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.15\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.14<\/td>\n<td>2026-06-27<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.14\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.13<\/td>\n<td>2026-06-13<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.13\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.12.post1<\/td>\n<td>2026-05-27<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.12.post1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.12<\/td>\n<td>2026-05-17<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.12\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.11<\/td>\n<td>2026-05-06<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.11\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.10.post1<\/td>\n<td>2026-04-09<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.10.post1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.10<\/td>\n<td>2026-04-06<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.10\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.9<\/td>\n<td>2026-02-24<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.9\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.8<\/td>\n<td>2026-01-24<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.8\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>gateway-v0.3.1 (Release Gateway-v0.3.1)<\/td>\n<td>2026-01-09<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/gateway-v0.3.1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.7<\/td>\n<td>2026-01-01<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.7\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>gateway-v0.3.0 (Release Gateway-v0.3.0)<\/td>\n<td>2025-12-25<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/gateway-v0.3.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>gateway-v0.2.4 (Release Gateway-v0.2.4)<\/td>\n<td>2025-12-10<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/gateway-v0.2.4\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.6<\/td>\n<td>2025-12-03<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.6\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>gateway-v0.2.3 (Release Gateway-v0.2.3)<\/td>\n<td>2025-11-17<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/gateway-v0.2.3\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>gateway-v0.2.2 (Release Gateway-v0.2.2)<\/td>\n<td>2025-11-17<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/gateway-v0.2.2\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>gateway-v0.2.1 (Release Gateway-v0.2.1)<\/td>\n<td>2025-11-17<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/gateway-v0.2.1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>gateway-v0.2.0 (Release Gateway-v0.2.0)<\/td>\n<td>2025-11-17<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/gateway-v0.2.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>gateway-v0.1.9 (Release Gateway-v0.1.9)<\/td>\n<td>2025-11-17<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/gateway-v0.1.9\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>gateway-v0.1.8 (Release Gateway-v0.1.8)<\/td>\n<td>2025-11-17<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/gateway-v0.1.8\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>gateway-v0.1.7 (Release Gateway-v0.1.7)<\/td>\n<td>2025-11-17<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/gateway-v0.1.7\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>gateway-v0.1.6 (Release Gateway-v0.1.6)<\/td>\n<td>2025-11-17<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/gateway-v0.1.6\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.5<\/td>\n<td>2025-11-07<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.5\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.4<\/td>\n<td>2025-10-26<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.4\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.3<\/td>\n<td>2025-10-07<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.3\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.2<\/td>\n<td>2025-09-12<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.2\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.5.1<\/td>\n<td>2025-08-24<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.5.1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.4.10<\/td>\n<td>2025-08-01<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.4.10\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.4.8<\/td>\n<td>2025-06-25<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.4.8\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.4.7<\/td>\n<td>2025-06-12<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.4.7\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.4.6<\/td>\n<td>2025-04-28<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.4.6\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.4.5<\/td>\n<td>2025-04-07<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.4.5\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.4.4<\/td>\n<td>2025-03-14<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.4.4\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.4.3<\/td>\n<td>2025-02-14<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.4.3\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.4.1<\/td>\n<td>2024-12-26<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.4.1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.4.0<\/td>\n<td>2024-12-04<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.4.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.3.6<\/td>\n<td>2024-11-22<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.3.6\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.3.4.post1<\/td>\n<td>2024-10-22<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.3.4.post1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.3.2<\/td>\n<td>2024-10-03<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.3.2\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.3.0<\/td>\n<td>2024-09-19<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.3.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.2.13<\/td>\n<td>2024-09-19<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.2.13\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.2.9<\/td>\n<td>2024-08-02<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.2.9\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.2.5<\/td>\n<td>2024-07-27<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.2.5\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.2.0<\/td>\n<td>2024-07-26<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.2.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.1.20<\/td>\n<td>2024-07-14<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.1.20\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.1.18<\/td>\n<td>2024-07-04<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.1.18\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.1.17<\/td>\n<td>2024-06-08<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.1.17\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.1.16<\/td>\n<td>2024-05-14<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.1.16\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.1.13<\/td>\n<td>2024-03-11<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.1.13\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.1.12<\/td>\n<td>2024-02-11<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.1.12\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.1.11<\/td>\n<td>2024-02-03<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.1.11\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.1.6<\/td>\n<td>2024-01-21<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.1.6\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.1.5<\/td>\n<td>2024-01-18<\/td>\n<td><a href=\"https:\/\/github.com\/sgl-project\/sglang\/releases\/tag\/v0.1.5\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h2>Articles on Local Model Watch<\/h2>\n<ul>\n<li>2026-09-19 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/19\/sglang-v0-5-20-released\/\">SGLang v0.5.20 Released: New Models and Optimizations<\/a><\/li>\n<\/ul>\n<p><em>Last updated 2026-09-19 (JST). Facts above come from the GitHub API; the one-paragraph summary is written by the site&#8217;s editors.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>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 [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-1250","page","type-page","status-publish","hentry"],"lang":"en","translations":{"en":1250,"ja":1248},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/1250","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/comments?post=1250"}],"version-history":[{"count":2,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/1250\/revisions"}],"predecessor-version":[{"id":1850,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/1250\/revisions\/1850"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=1250"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}