[BUGFIX] Fix regex pattern for Mistral Tool Call (#29918)

Julien Denize committed 11 months ago

[BUGFIX] llama_4_scaling wrongly passed to DeepseekAttention (#29908)

Julien Denize committed 11 months ago

[Bugfix] fix --scheduling-policy=priority & n>1 crashes engine (#29764)

Chauncey committed 11 months ago

[Bugfix][EPLB] Prevent user-provided EPLB config from being overwritten with defaults (#29911)

Sage Moore committed 11 months ago

Fix some more Transformers nightly tests (#29872)

Harry Mellor committed 11 months ago

Bump actions/setup-python from 6.0.0 to 6.1.0 (#29768)

dependabot[bot] committed 11 months ago

[Perf] Avoid pageable HtoD transfer in MinTokensLogitsProcessor (#29826)

jthomson04 committed 11 months ago

[CI][ROCm][tests/v1/e2e] Fix multiprocessing launch for the test (#29123)

Divakar Verma committed 11 months ago

Fix boolean nested params, add dict format support, and enhance plotting for vllm bench sweep (#29025)

Copilot committed 11 months ago

feat(model): Add BitsAndBytes quantization support for Qwen3-Omni-MoE (#29896)

Navanit Dubey committed 11 months ago

[Attention][CUDAGraph] Remove CG padding from attention backends (#29352)

Matthew Bonanni committed 11 months ago

[CI/Build] Fixes missing runtime dependencies (#29822)

Benjamin Bartels committed 11 months ago

Update AMD-CI testing mirror (as of 2025-12-02) (#29898)

Alexei-V-Ivanov-AMD committed 11 months ago

[Chore]: Reorganize gguf utils funtions under `transformers_utils` (#29891)

Isotr0py committed 11 months ago

[responsesAPI][3] ResponsesParser to set up non harmony MCP (#29413)

Andrew Xia committed 11 months ago

[Bugfix] Fix incorrect channel order for idefics3 in edge case (#29881)

Isotr0py committed 11 months ago

[examples] Resettle pooling examples. (#29365)

wang.yuqi committed 11 months ago

[Bugfix] Fix DeepSeek R1 MTP weight loading (#29545)

Matthew Bonanni committed 11 months ago

[Multimodal][Core] Optimize multimodal preprocessing cache by hashing image bytes instead of pixel values (#29621)

ImaGoodFella committed 11 months ago

[Chore] Use `tokenizer.encode` and `tokenizer.decode` directly (#29851)

Cyrus Leung committed 11 months ago