update CODEOWNERS file (#39439)

Chendi.Xue committed 7 months ago

[Perf] Reduce H2D pageable memory copies (#38794)

Chaofan Wang committed 7 months ago

[Core] Change max_model_len in EngineCoreReadyResponse to be non-None (#39442)

Nick Hill committed 7 months ago

Add platform manual_seed_all API (#38468)

Yan Ma committed 7 months ago

[BugFix][CPU] Add CPU profiler summary file output (#38366)

Elham committed 7 months ago

[Bugfix] Fix broken explicit unquantized kv cache dtype support (#38922)

Isotr0py committed 7 months ago

[feat]: make DCP error msg clearer (#28443)

Srreyansh Sethi committed 7 months ago

[KV Offload] Implement `shutdown()` in `OffloadingConnector` and related classes (#39182)

Ronen Schaffer committed 7 months ago

[Mergify] Update model vendor auto-label rules (#39312)

Cyrus Leung committed 7 months ago

Add EXAONE-4.5 (#39388)

Kyungmin Lee committed 7 months ago

[BugFix] Fix OOB read in CUTLASS grouped GEMM with epilogue (#38571)

Lucas Wilkinson committed 7 months ago

feat(cpu): add CPU support for draft model speculative decoding (#32662)

Ganesh R committed 7 months ago

[CT][FP8][Marlin] refactor CompressedTensorsW8A16Fp8 to use kernel abstraction (#38244)

Kunshang Ji committed 7 months ago

[Feature] Add auto-detection for reasoning_config when only reasoning_parser is set (#38214)

Chauncey committed 7 months ago

[ROCm] Fix AITER ops fake impl and minor bugs (#36092)

Chuan (Richard) Li committed 7 months ago

fix(gdn): Align prefill warmup with real prefill path (#39169)

Ibrahim Arshad committed 7 months ago

[Model][Perf] Enable checkpoints prefetching for Lustre FS by default (#39422)

Artem Perevedentsev committed 7 months ago

[LMCache] vLLM Block Allocation Event (#38856)

Yuwei An committed 7 months ago

[CI/Build[ Don't auto-rebase PRs with CI failures (#39443)

Cyrus Leung committed 7 months ago

[Spec Decode] fix returning size mismatch on extract hidden states proposer (#38610)

zzaebok committed 7 months ago