Fix some typo (#19475)

Ximingwang-09 committed over 1 year ago

Add cache to cuda get_device_capability (#19436)

Michael Goin committed over 1 year ago

Support non-string values in JSON keys from CLI (#19471)

Cyrus Leung committed over 1 year ago

[Misc] Reduce warning message introduced in env_override (#19476)

Lu Fang committed over 1 year ago

[Doc] Support "important" and "announcement" admonitions (#19479)

Cyrus Leung committed over 1 year ago

[Doc] Fix quantization link titles (#19478)

Cyrus Leung committed over 1 year ago

[Doc] Update V1 User Guide for Hardware and Models (#19474)

Cyrus Leung committed over 1 year ago

[Kernel] Support deep_gemm for linear methods (#19085)

artetaout committed over 1 year ago

[ROCm] Add rules to automatically label ROCm related PRs (#19405)

Lu Fang committed over 1 year ago

Fix Typo in Documentation and Function Name (#19442)

leopardracer committed over 1 year ago

Add fused MOE config for Qwen3 30B A3B on B200 (#19455)

Junhao Li committed over 1 year ago

[Misc] Remove unused `MultiModalHasher.hash_prompt_mm_data` (#19422)

Lukas Geiger committed over 1 year ago

[CI] Disable failing GGUF model test (#19454)

Michael Goin committed over 1 year ago

Fix test_max_model_len in tests/entrypoints/llm/test_generate.py (#19451)

Lu Fang committed over 1 year ago

[BugFix] Fix docker build cpu-dev image error (#19394)

niu_he committed over 1 year ago

[New Model]: Support Qwen3 Embedding & Reranker (#19260)

wang.yuqi committed over 1 year ago

[BugFix] Allow use_cudagraph to work with dynamic VLLM_USE_V1 (#19390)

Richard Zou committed over 1 year ago

Add H20-3e fused MoE kernel tuning configs for Qwen3-235B-A22B-FP8 (#19401)

Xu Wenqing committed over 1 year ago

[Model] use AutoWeightsLoader for commandr (#19399)

py-andy-c committed over 1 year ago

[ROCm][V1] Adding ROCm to the list of plaforms using V1 by default (#19440)

Gregory Shtrasberg committed over 1 year ago