[Bugfix]: Installing dev environment due to pydantic incompatible version (#23353)

Martin Hickey committed about 1 year ago

[Fix] Bump triton version in rocm-build requirements (#21630)

Burkhard Ringlein committed about 1 year ago

[Bug fix] Dynamically setting the backend variable for genai_perf_tests in the run-nightly-benchmark script (#23375)

Naman Lalit committed about 1 year ago

[Misc] local import code clean (#23420)

Ning Xie committed about 1 year ago

[Doc] Update the doc for log probs + prefix caching (#23399)

Chen Zhang committed about 1 year ago

[misc] Remove outdate comment about runai_model_streamer (#23421)

杨朱 · Kiki committed about 1 year ago

[Attention] Allow V1 flash_attn to support cross-attention (#23297)

Russell Bryant committed about 1 year ago

[Misc] Move M-RoPE init logic to _init_mrope_positions (#23422)

Woosuk Kwon committed about 1 year ago

[V0 Deprecation] Remove V0 LoRA test (#23418)

Jee Jee Li committed about 1 year ago

[Bugfix] Fix pooling models on CPU backend (#23392)

Li, Jiang committed about 1 year ago

Migrate MiniCPMOAudioInputs to TensorSchema (#21847)

Benji Beck committed about 1 year ago

[gpt-oss] add input/output usage in responses api when harmony context is leveraged (#22667)

Guillaume Calmettes committed about 1 year ago

[P/D][Nixl] Make kv cache register compatible with hybrid memory allocator (#23079)

Flora Feng committed about 1 year ago

[Attention] Refactor AttentionMetadata Preparation for Encoder-only Models (#23154)

Chen Zhang committed about 1 year ago

[New Model] Add Seed-Oss model (#23241)

Bin Jia committed about 1 year ago

[Misc] Add gemma3 chat template with pythonic-style function calling (#17149)

Philip Chung committed about 1 year ago

[CI] Add end-to-end V1 min_tokens test coverage (#22495)

Arjun Reddy committed about 1 year ago

[Feature] Enable DeepGEMM Linear on B200; 1.5% E2E throughput improvement (#23351)

Wentao Ye committed about 1 year ago

[CI/Build] Skip Idefics3 and SmolVLM generation test again (#23356)

Isotr0py committed about 1 year ago

Migrate MllamaImagePixelInputs to TensorSchema (#22020)

Benji Beck committed about 1 year ago