[Model] Support Mistral3 in the HF Transformers format (#15505)

Michael Goin committed over 1 year ago

setup correct nvcc version with CUDA_HOME (#15725)

Yang Chen committed over 1 year ago

[Misc] Use envs.VLLM_USE_RAY_COMPILED_DAG_CHANNEL_TYPE (#15831)

Rui Qiao committed over 1 year ago

[Bugfix] Fix no video/image profiling edge case for `MultiModalDataParser` (#15828)

Isotr0py committed over 1 year ago

[Docs] Fix small error in link text (#15868)

Harry Mellor committed over 1 year ago

[Misc] Fix speculative config repr string (#15860)

shangmingc committed over 1 year ago

[Misc] Enable V1 LoRA by default (#15320)

Varun Sundar Rabindranath committed over 1 year ago

[Feature] specify model in config.yaml (#15798)

Wei Zeng committed over 1 year ago

fix: can not use uv run collect_env close #13888 (#15792)

yihong committed over 1 year ago

[V1] Implement sliding window attention in kv_cache_manager (#14097)

Chen Zhang committed over 1 year ago

[ROCm] Use device name in the warning (#15838)

Gregory Shtrasberg committed over 1 year ago

[sleep mode] clear pytorch cache after sleep (#15248)

Lionel Villard committed over 1 year ago

[V1] TPU - Fix fused MOE (#15834)

Alexander Matveev committed over 1 year ago

[Bugfix]: Fix is_embedding_layer condition in VocabParallelEmbedding (#15824)

Alexey Kiryushin committed over 1 year ago

[Bugfix] Fix extra comma (#15851)

Percy committed over 1 year ago

[Bugfix][Model] fix mllama multi-image (#14883)

Yan Ma committed over 1 year ago

[Frontend] Add Phi-4-mini function calling support (#14886)

Kinfey committed over 1 year ago

Rename fallback model and refactor supported models section (#15829)

Harry Mellor committed over 1 year ago

[Distributed] Add custom allreduce support for ROCM (#14125)

Ilya Markov committed over 1 year ago

Move dockerfiles into their own directory (#14549)

Harry Mellor committed over 1 year ago