SGLang v0.5.19 lands beam search, DeepEP v2, and Qwen3.8 support across 786 PRs

Tools official 1 src. ~1 min

SGLang v0.5.19 (Sep 5, 786 PRs from 214 contributors) adds Qwen3.8 (2.4T-A95B) and Qwen3.8-27B plus dots3.note, Ling-3.0, Spark2.5 and Granite 4.2; introduces beam search via `beam_width`, the DeepEP v2 ElasticBuffer all-to-all backend, LayerNorm sequence parallelism (−3.5% prefill on H100), W4A8 MoE on Hopper, decode context parallelism on the default Blackwell MLA backend, a persistent Lean attention kernel on AMD MI300X/MI355X (up to 1.52x throughput), and makes the unified radix tree the default cache.

Why it matters

beam search and DeepEP v2 bring training-grade decoding options to production serving

Importance: 2/5

notable minor release with broad model and backend support

Sources

official SGLang v0.5.19