[Feature] Change cache.py with pydantic validation (#26390)

Vinay R Damodaran committed about 1 year ago

Remove Python 3.9 support ahead of PyTorch 2.9 in v0.11.1 (#26416)

Harry Mellor committed about 1 year ago

[Bug] Fix Test in Batch Invariant (#26128)

Wentao Ye committed about 1 year ago

[Benchmarks] Fix imports in FP8 tuning script (#26407)

Lukas Geiger committed about 1 year ago

[Bug] Fix DeepGEMM Attention Test (#26423)

Wentao Ye committed about 1 year ago

[Bugfix] Fix `vllm bench ...` on CPU-only head nodes (#25283)

Aydin Abiar committed about 1 year ago

[CI Failure] Fix pre-commit issue for install_nixl_from_source_ubuntu.py (#26424)

Michael Goin committed about 1 year ago

[Refactor] Refactor FP8 & INT8 Quant Folder inside `w8a8` (#25293)

Wentao Ye committed about 1 year ago

[NIXL][non-cuda] Add install script for nixl with non-cuda ucx (#25959)

Chendi.Xue committed about 1 year ago

Tidy `vllm/config/__init__.py` to only add classes and functions (#26405)

Harry Mellor committed about 1 year ago

[Benchmarks] Add support for Qwen 3 VL MoE tuning (#26419)

Lukas Geiger committed about 1 year ago

[CI] Pooling models mteb test disable enforce_eager (#26408)

wang.yuqi committed about 1 year ago

[Docs] Have mergify leave a comment with the docs preview link (#26412)

Harry Mellor committed about 1 year ago

[Model] Allow passing custom number of max tiles to Nano 2 VL (#26403)

Eugene Khvedchenya committed about 1 year ago

[Misc] add `usedforsecurity=False` in md5 hash call (#26357)

Daniele committed about 1 year ago

[Feature] Enable E8M0 by Default on Hopper for DeepGEMM, 5% E2E throughput improvement (#26197)

Wentao Ye committed about 1 year ago

[TPU] Rename tpu_commons to tpu_inference (#26279)

Utkarsh Sharma committed about 1 year ago

fix[DP][v1]: Prevent hangs from mismatched worker configurations (#26218)

Ayush Satyam committed about 1 year ago

[Bugfix] Incorrect MM data format in `vllm bench throughput` (#26395)

Cyrus Leung committed about 1 year ago

Add gather_indexer_k_quant_cache kernel (#25931)

Barry Kang committed about 1 year ago