[Doc] Add usage of implicit text-only mode (#22561)

Roger Wang committed over 1 year ago

Implicit language-model-only mode via limit-mm-per-prompt (#22299)

Roger Wang committed over 1 year ago

[Bugfix] Fix ModernBert cuda graph capturing in v1 (#21901)

Isotr0py committed over 1 year ago

[BugFix] [P/D] Handle lookahead token count edge-case with Eagle Spec Decoding and P/D (#22317)

Pradyun92 committed over 1 year ago

[XPU] upgrade torch 2.8 on for XPU (#22300)

Kunshang Ji committed over 1 year ago

Drop flaky test_healthcheck_response_time (#22539)

Russell Bryant committed over 1 year ago

Extract `CompilationConfig` from `config.py` (#22524)

Harry Mellor committed over 1 year ago

[Frontend] Add unix domain socket support (#18097)

yyweiss committed over 1 year ago

[Docs] fix broken links in metrics.md (#22315)

Guy Stone committed over 1 year ago

Skip Qwen 1 in CI because remote code is no longer compatible with Transformers (#22536)

Harry Mellor committed over 1 year ago

[Bugfix] Update FA commit hash (#22546)

Thomas Parnell committed over 1 year ago

[Misc] DeepGEMM : Avoid JIT generation in the hot-path (#22215)

Varun Sundar Rabindranath committed over 1 year ago

[BugFix] Fix IMA FlashMLA full cuda-graph and DP + Update FlashMLA (#21691)

Lucas Wilkinson committed over 1 year ago

[gpt-oss] Support tool call and implement MCP tool server (#22427)

Chen Zhang committed over 1 year ago

[Docs] Rename “Distributed inference and serving” to “Parallelism & Scaling” (#22466)

Ricardo Decal committed over 1 year ago

[gpt-oss] guard import when triton kernel is not installed (#22529)

Yongye Zhu committed over 1 year ago

[Benchmark] Add benchmark tool for multi turn conversations (#20267)

Daniel Serebrenik committed over 1 year ago

[gpt-oss] triton kernel mxfp4 (#22421)

Yongye Zhu committed over 1 year ago

Remove exception for Python 3.8 typing from linter (#22506)

Harry Mellor committed over 1 year ago

[Docs] Improve API docs (+small tweaks) (#22459)

Harry Mellor committed over 1 year ago