v0.5.20
Highlights 713 PRs from 237 contributors. New models in this release (see the cookbook for all supported models): Model Type PRs Cookbook GLM-5.3-Flash…
What moved
Highlights 713 PRs from 237 contributors. New models in this release (see the cookbook for all supported models): Model Type PRs Cookbook GLM-5.3-Flash Autoregressive #36507 , #38621 link Hy4-Preview Autoregressive #36805 link Qwen3.8-Flash-Next Autoregressive #37500 link K2 Horizon Autoregressive #37654 , #38033 link Nanbeige4.2 Autoregressive #32151 SenseNova-U1.5-8B-MoT Diffusion #36606 link FastH3 (4-step MiniMax-H3 distill) Diffusion #37480 link VDN-H3 (hybrid-attention MiniMax-H3 distill) Diffusion #37903 link Sampling masks for RL rollouts. With return_sampling_mask , each decode step returns the exact token support.
Why it matters
Highlights 713 PRs from 237 contributors. That is a public launch file from SGLang, dated 2026-09-18. Tagged LLM / Hardware.
On the record
- Filed from the SGLang official RSS on 2026-09-18.
- Primary source host: github.com.
- Highlights 713 PRs from 237 contributors.
github.com
Logged as brief 007