[docs] promo pytorch conf and ray summit (#24562)

Simon Mo committed about 1 year ago

[Docs] Enable relative links in examples to function when rendered in the docs (#24041)

Harry Mellor committed about 1 year ago

[Bugfix] Update Run:AI Model Streamer Loading Integration (#23845)

pwschuurman committed about 1 year ago

[Core] Simplify and unify mm uuid handling & auto-generated mm hash overrides processing. (#24271)

Chenheli Hua committed about 1 year ago

[gpt-oss] Cache permute indices for faster MXFP4 MoE layer loading (#24154)

Wei committed about 1 year ago

[BugFix][Spec Decode] Fix out-of-range index triggered by eagle3; re-enable test for LlamaForCausalLMEagle3 (#24392)

Wenlong Wang committed about 1 year ago

[P/D] MultiConnector supports shutdown (#24425)

Chauncey committed about 1 year ago

[KV Connector] More async support for `get_num_new_matched_tokens` (#23620)

Yihua Cheng committed about 1 year ago

[CI] Adjust threshold for flaky ngram spec decoding test (#24528)

Nick Hill committed about 1 year ago

[BugFix] Fix async core engine client finalizer (#24540)

Nick Hill committed about 1 year ago

[Hardware][Apple-CPU] Enable native bfloat16 on Apple Silicon (M2 and later) (#24129)

Ignacio Sica committed about 1 year ago

[CI] Retry flaky fp8 cutlass mla tests (#24536)

Nick Hill committed about 1 year ago

Add @heheda12345 to CODEOWNERS of KVCacheManager related code (#24546)

Chen Zhang committed about 1 year ago

[Perf] Convert np array to torch tensor to index into block table for attn chunking (#24474)

Yong Hoon Shin committed about 1 year ago

[Bugfix] Fix for 24530. Fix naive all2all shared expert overlap. (#24538)

bnellnm committed about 1 year ago

[Bugfix] Improve EPLB config validation error message (#24524)

Tyler Michael Smith committed about 1 year ago

[ROCm][Feature] Enable Pipeline Parallelism with Ray Compiled Graph on ROCm (#24275)

Charlie Fu committed about 1 year ago

[Benchmark] Add option to skip oversampling in benchmark (#24457)

Ekagra Ranjan committed about 1 year ago

[Benchmark] Update bench doc with mtbench, blazedit, spec bench (#24450)

Ekagra Ranjan committed about 1 year ago

[Log] Use a relative path in debug-level logs to distinguish files with identical names (#23846)

Jiangyun Zhu committed about 1 year ago