[Doc] fix the incorrect module path of tensorize_vllm_model (#13863)

Albert committed over 1 year ago

Improve pipeline partitioning (#13839)

Harry Mellor committed over 1 year ago

[Kernel][Build/CI] Bump CUTLASS to 3.8 and add initializers for cutlass epilogues (#13797)

Henry Tsang committed over 1 year ago

[Misc]Code Cleanup (#13859)

Chenguang Li committed over 1 year ago

[V1][Spec Decode] Change Spec Decode Rejection Sampling API (#13729)

Lily Liu committed over 1 year ago

[misc] Show driver IP info when Ray fails to allocate driver worker (#13858)

Rui Qiao committed over 1 year ago

DeepSeek V2/V3/R1 only place `lm_head` on last pp rank (#13833)

Harry Mellor committed over 1 year ago

[Model] Support Grok1 (#13795)

Michael Goin committed over 1 year ago

Fix failing `MyGemma2Embedding` test (#13820)

Harry Mellor committed over 1 year ago

[Neuron] Add custom_ops for neuron backend (#13246)

Liangfu Chen committed over 1 year ago

Fix string parsing error (#13825)

Chen1022 committed over 1 year ago

[Bugfix] Revert inspection code in #13743 (#13832)

Cyrus Leung committed over 1 year ago

Fix `/v1/audio/transcriptions ` Bad Request Error (#13811)

Wen Sun committed over 1 year ago

[Bugfix] Fix deepseek-vl2 inference with more than 2 images (#13818)

Isotr0py committed over 1 year ago

[Bugfix] Flush TunableOp results before worker processes are destroyed. (#13623)

Nichols A. Romero committed over 1 year ago

[Bugfix] Initialize attention bias on the same device as Query/Key/Value (#13468)

Junlin Zhou committed over 1 year ago

[Misc]Clarify Error Handling for Non-existent Model Paths and HF Repo IDs (#13724)

Chen1022 committed over 1 year ago

[CI/Build] Fix V1 LoRA failure (#13767)

Jee Jee Li committed over 1 year ago

[ROCm][Quantization][Kernel] Using HIP FP8 header (#12593)

Gregory Shtrasberg committed over 1 year ago

[Feature] Support KV cache offloading and disagg prefill with LMCache connector. (#12953)

Jiayi Yao committed over 1 year ago