[CI/Build] Add tests for the V1 tpu_model_runner. (#14843)

yarongmu-google committed over 1 year ago

[bugfix] fix inductor cache on max_position_embeddings (#15436)

youkaichao committed over 1 year ago

[Kernel] Fix conflicting macro names for gguf kernels (#15456)

Szymon Ożóg committed over 1 year ago

[Doc] Update V1 user guide for multi-modality (#15460)

Cyrus Leung committed over 1 year ago

[Misc] Remove redundant `num_embeds` (#15443)

Cyrus Leung committed over 1 year ago

[Misc] Clean up MiniCPM-V/O code (#15337)

Cyrus Leung committed over 1 year ago

Dockerfile.ppc64le changes to move to UBI (#15402)

Md. Shafi Hussain committed over 1 year ago

[Kernel][CPU] CPU MLA (#14744)

Thien Tran committed over 1 year ago

[Hardware][TPU][Bugfix] Fix v1 mp profiler (#15409)

Siyuan Liu committed over 1 year ago

Fix CUDA kernel index data type in vllm/csrc/quantization/gptq_marlin/awq_marlin_repack.cu +10 (#15160)

Lu Fang committed over 1 year ago

[V1][Spec Decode] Update target_logits in place for rejection sampling (#15427)

Woosuk Kwon committed over 1 year ago

[V1] guidance backend for structured output + `auto` fallback mode (#14779)

Russell Bryant committed over 1 year ago

[Bugfix] Fixed the issue of not being able to input video and image simultaneously (#15387)

Chauncey committed over 1 year ago

Revert "Fix non-contiguous input passed to Marlin kernel (#15319)" (#15398)

Tyler Michael Smith committed over 1 year ago

[Misc] Remove LoRA log (#15388)

Jee Jee Li committed over 1 year ago

Add pipeline parallel support to `TransformersModel` (#12832)

Harry Mellor committed over 1 year ago

[Minor][Spec Decode] Remove compiled_softmax (#15416)

Woosuk Kwon committed over 1 year ago

[V1][Spec Decode] Enable spec decode for top-p & top-k sampling (#15063)

Woosuk Kwon committed over 1 year ago

[ROCm][Kernel] MoE weights padding (#14454)

Gregory Shtrasberg committed over 1 year ago

[Build] Cython compilation support fix (#14296)

Gregory Shtrasberg committed over 1 year ago