[LMCache MP Patch]: Race Condition + Duplicated Block Ids (#35831)

Samuel Shen committed 8 months ago

[Bugfix][LMCache][KVConnector] fix potential memory leak in LMCache multiprocess mode (#35931)

Roy Huang committed 8 months ago

[compile] Split compile/warmup monitoring (#36098)

Richard Zou committed 8 months ago

[Perf] Support FP8 KV cache for Flashinfer MLA Sparse (#35891)

Wei Zhao committed 8 months ago

[Core] NGram GPU Implementation compatible with Async Scheduler (#29184)

PatchyTIS committed 8 months ago

[ROCm][CI] Accept Different But Valid Output for `test_olmoe_tp` (#35224)

Micah Williamson committed 8 months ago

[ROCm][CI] Enable AITER for failing `test_gpt_oss` test case on MI355 (#36174)

Micah Williamson committed 8 months ago

[CI] Enable Crosslayer KV layout tests for ROCm platforms (#35416)

qli88 committed 8 months ago

[UX][Startup] Account for CUDA graphs during memory profiling (#30515)

Matthew Bonanni committed 8 months ago

Adding support to Sarvam's MoE models (#33942)

rahul-sarvam committed 8 months ago

[Misc] Remove duplicate parser registration (#36303)

Taneem Ibrahim committed 8 months ago

[V0 Deprecation] Remove unused swap_space parameter (#36216)

lif committed 8 months ago

[Bugfix] Fix compressed-tensors quantization failure for DeepSeek-R1 on MI300x (#36247)

vllmellm committed 8 months ago

feat: expose media_io_kwargs at runtime (#34778)

milesial committed 8 months ago

[ROCm][CI] Making entrypoints more deterministic on ROCm (#36293)

Andreas Karatzas committed 8 months ago

Fix CUDA graph decode capture crash in AITER FlashAttention (#36042)

Mengtao (Martin) Yuan committed 8 months ago

refine `vllm bench throughput --backend hf` (#35971)

Kunshang Ji committed 8 months ago

[BugFix] Avoid ignored trust_remote_code warnings (#36290)

Nick Hill committed 8 months ago

[Model Runner V2] Fix warmup for pipeline parallel (#36280)

Nick Hill committed 8 months ago

[Core] Fix benign error log during normal shutdown (#36270)

Nick Hill committed 8 months ago