[ROCm][Fix] Fix rocm build caused by #23791 (#23847)

Charlie Fu committed about 1 year ago

[Models] Improve iteration over layers (#19497)

Lukas Geiger committed about 1 year ago

[XPU] support data parallel for MoE models on XPU (#22887)

Chaojun Zhang committed about 1 year ago

[V0 Deprecation] Remove V0 Samplers test (#23862)

Woosuk Kwon committed about 1 year ago

[Log] Use Debug Once for DeepGEMM E8M0 When not Enabled (#23858)

Wentao Ye committed about 1 year ago

[V1] Enable prefill optimization for Gemma3n (#22628)

Yong Hoon Shin committed about 1 year ago

[BugFix][FlashInfer] Fix potential race condition for paged_kv_indptr_cpu (#23737)

Woosuk Kwon committed about 1 year ago

chore: build release image by default (#23852)

Simon Mo committed about 1 year ago

[NVIDIA] Support SiluMul + NVFP4 quant fusion (#23671)

elvischenv committed about 1 year ago

[bugfix] [spec-decoding] fix data race in sample_recovered_tokens_kernel (vLLM v1) (#23829)

Jingkai He committed about 1 year ago

[ROCm][Aiter] Add triton fp8 bmm kernel for mla (#23264)

Divakar Verma committed about 1 year ago

Migrate Llama4ImagePatchInputs to TensorSchema (#22021)

Benji Beck committed about 1 year ago

Add scale_config.yml file for Meta autoscalers for GH Actions (#23840)

Jean Schmidt committed about 1 year ago

[ci] breaks down V1 Test into 3 groups of approx 30 minutes runtime (#23757)

Jean Schmidt committed about 1 year ago

[Bugfix] Add fake mode around passes (#23349)

Angela Yi committed about 1 year ago

[Model][gpt-oss] Support DP+EP for GPT-OSS with FlashInfer trtllm-gen MoE (#23819)

Po-Han Huang (NVIDIA) committed about 1 year ago

[CI] Fix linting error on main (#23835)

Thomas Parnell committed about 1 year ago

[Bugfix] Fix benchmark_moe.py for blockwise fp8. (#23823)

YUQI.CHENG committed about 1 year ago

[Doc]: fix typos in Python scripts (#23828)

Didier Durand committed about 1 year ago

[Model] [gpt-oss] fix gpt-oss pp support (#23815)

Jiangyun Zhu committed about 1 year ago