[Core] Move save_tensorized_model logic to Worker (#35825)

Nick Hill committed 8 months ago

[Model Runner V2] support dp & ep for spec decoding (#35294)

zhrrr committed 8 months ago

[CI/Build] Allow mounting AWS credentials for sccache S3 auth (#35912)

Amr Mahdi committed 8 months ago

[Model Runner V2] Fix inputs_embeds=None bug for MM models (#35917)

Woosuk Kwon committed 8 months ago

[Bugfix] Fix misnamed parameter in compressed_tensors_moe.py (#35813)

bnellnm committed 8 months ago

[ROCm][CI] Fix TP size issue for `test_gpt_oss` (#35887)

Micah Williamson committed 8 months ago

[ROCm][Bugfix]: Disable AITER Triton ROPE by default (#35601)

Rohan Potdar committed 8 months ago

[MoE Refactor] Create MK for TRTLLM Kernels (#32564)

Robert Shaw committed 8 months ago

[CI] Temporarily Disable Llama4 MoE Refactor Test (#35870)

Robert Shaw committed 8 months ago

[CI] Bump `num_speculative_tokens` to 3 in nightly DeepSeek tests (#35882)

Matthew Bonanni committed 8 months ago

fix: Ensure invalid audio files return 400 error (#34715)

JasonCohere committed 8 months ago

TRTLLM gen-full attn Test Coverage (#34986)

ojhaanshika committed 8 months ago

[BugFix] Add support for MTP num_speculative_tokens > 1 with sparse MLA (#34552)

Lucas Wilkinson committed 8 months ago

[ROCm] [CI] Add new fusion test cases that are relevant to vLLM IR Ops (#34307)

TJian committed 8 months ago

[Frontend][1/n] Improve pooling entrypoints | classify. (#35604)

wang.yuqi committed 8 months ago

[Bugfix] Avoid src/dst as None in irecv/isend_tensor_dict (#35754)

Li, Jiang committed 8 months ago

[CI] And PPL test for Qwen3.5. (#35853)

wang.yuqi committed 8 months ago

[Perf] [Hybrid] Copy num_accepted_tokens in non-blocking way when not using prefix caching (#35442)

Thomas Parnell committed 8 months ago

[CI/Build][Intel] Add new performance benchmarks for Intel Gaudi 3 (#31025)

Szymon Reginis committed 8 months ago

add regression test (#35834)

hallerite committed 8 months ago