triple-muandmickqian bf71035d39 [diffusion] MiniMax-H3: tiered AdaLN plan cache (pinned-host tier + per-plan LRU) (#37266) ...

Co-authored-by: mickqian <mickqian@users.noreply.github.com>

2026-09-03 22:09:21 +08:00

..

advanced_features

[Speculative Decoding] Add native UNO serving support (#37667)

2026-09-03 20:08:41 +08:00

basic_usage

fix(openai): avoid duplicate routed expert in response when return_meta_info = True (#35323)

2026-08-20 15:21:58 -07:00

developer_guide

[bench] Support real-traffic replay with early-stop-aware steady-state metrics in bench_one_batch_server (#37469)

2026-09-02 17:20:25 -07:00

get-started

[Docs] Add --prerelease=allow to cookbook uv install commands (#35920)

2026-08-21 15:51:48 -07:00

hardware-platforms

[NPU] [DOC] Refresh supported models and features on NPU (#37799)

2026-09-03 19:53:39 +08:00

references

feat(kernels): generalize persistent CuTe JIT cache (#33911)

2026-09-02 19:59:04 -07:00

sglang-diffusion

[diffusion] MiniMax-H3: tiered AdaLN plan cache (pinned-host tier + per-plan LRU) (#37266)

2026-09-03 22:09:21 +08:00

supported-models

Add SGLang Granite SWA support via existing Granite models (#35794)

2026-08-21 11:13:15 -07:00

supported-models.mdx

[Docs] Rename docs_new/ to docs/ (#32123)

2026-08-03 16:51:00 -07:00