3 people b8ec544946 [DSA] Integrate Q8KV8 FP8 Sparse MLA Prefill into the DSA Backend (DeepSeek-V3.2) (#30514) ...

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>

2026-07-19 11:58:16 +08:00

..

advanced_features

[DSA] Integrate Q8KV8 FP8 Sparse MLA Prefill into the DSA Backend (DeepSeek-V3.2) (#30514)

2026-07-19 11:58:16 +08:00

basic_usage

Remove legacy Sphinx docs/ and finish the Mintlify cutover (#28964)

2026-07-13 15:06:08 -07:00

developer_guide

[JIT] Refactor dtype traits into DTypeTrait and unify warp reductions (#30838)

2026-07-18 10:07:18 +08:00

get-started

chore: bump docs install version to 0.5.15 (#31058)

2026-07-13 18:58:48 +00:00

hardware-platforms

Remove deprecated Mamba flags from doc, wrong FP8 GEMM docstrings and change Nemotron image to 0.5.15 (#31094)

2026-07-17 14:34:29 -07:00

references

[Scheduler] Add SGLANG_MAX_NEW_TOKENS_LIMIT to cap per-request max_new_tokens (#22591)

2026-07-16 21:34:10 -07:00

sglang-diffusion

[Diffusion] Use SGLang server for ERNIE-Image prompt enhancement (#31354)

2026-07-18 06:55:28 +03:00

supported-models

[Model] Add support for JetBrains' Mellum v2 code generation model (#27375)

2026-07-13 22:54:38 -07:00

supported-models.mdx

[Docs] Sync docs_new with legacy docs and update migration redirects (#23337)

2026-04-21 00:15:17 -07:00