[CI] Fix segfault in tracing test (#47299)

Nick Hill committed 4 months ago

Migrate GPTBigCode and Starcoder2 to the Transformers modeling backend (#30966)

Harry Mellor committed 4 months ago

docs(security): document gRPC interface as insecure for private use only (#45903)

Juan Pérez de Algaba committed 4 months ago

[ROCm][MiniMax-M3] Cross-layer lightning-indexer top-k sharing (#47269)

Fangzhou Ai committed 4 months ago

[Model] Remove AyaVision, MusicFlamingo (#47263)

Harry Mellor committed 4 months ago

[Model] Support Hy3 token suffix and JSON Schema array types (#47192)

stevenkuang committed 4 months ago

[Bugfix] Expose usage field in GenerateResponse for disaggregated serving (#42748)

Aleksei Ivashov committed 4 months ago

[CI] Fix various failures on `main` (#47197)

Harry Mellor committed 4 months ago

[ROCm][Perf][Bugfix] DSv4 indexer: use platform FP8 dtype (fnuz) for Q-quant on gfx942 (#46730)

akii96 committed 4 months ago

[Bugfix] Fix pooled Whisper sliding-window KV sizing (#47071)

Andy Lo committed 4 months ago

[Test] Run SageMaker handler-override tests in-process via TestClient (#47250)

Jyothirmai Kottu committed 4 months ago

[ROCm][DSV4] Use aiter mHC pre/post as the default ROCm path (#43950)

Fangzhou Ai committed 4 months ago

Weight sync refactor + move sparse nccl engine (#44353)

Aaron Hao committed 4 months ago

[XPU][UT]Enable ut qk_norm_rope_fusion (#42486)

Yejing Lai committed 4 months ago

[CI/Build] Fix LoRA testing (#47242)

Jee Jee Li committed 4 months ago

[Core] Make sleep-mode backend capability flags communicator-agnostic (#47243)

Nils Matteson committed 4 months ago

Remove mantis (#46806)

Tiezhen WANG committed 4 months ago

[Bugfix] Fix beam search candidate indexing when logprobs count varies (#47126)

Chauncey committed 4 months ago

[Rust Frontend] Coerce completion `max_tokens: null` to default (#47166)

Blas Rodriguez Irizar committed 4 months ago

[CPU][Perf]Added tanh AOR for faster gelu activations. (#44639)

almayne committed 4 months ago