Skip to content

Actions: CentML/vllm

Actions

pre-commit

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-commit.yml
159 workflow runs
159 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Bump ray from 2.48.0 to 2.52.0 in /requirements pre-commit #159: Pull request #15 synchronize by dependabot bot
3m 25s dependabot/pip/requirements/ray-2.52.0
dependabot/pip/requirements/ray-2.52.0
3m 25s
[TPU] add tpu_inference (#27277) pre-commit #158: Commit ba1fcd8 pushed by vadiklyutiy
3m 12s main
main
3m 12s
Bump ray from 2.48.0 to 2.52.0 in /requirements pre-commit #157: Pull request #15 opened by dependabot bot
3m 35s dependabot/pip/requirements/ray-2.52.0
dependabot/pip/requirements/ray-2.52.0
3m 35s
[Kernel] Use pre-allocated output buffer for triton kernel fused_expe… pre-commit #156: Commit 53d7f1f pushed by wangshangsam
3m 52s main
main
3m 52s
[caching] Add enable_prompt_embeds and cpu_offload_gb to compile hash… pre-commit #155: Commit 0abc794 pushed by wangshangsam
3m 31s main
main
3m 31s
[CI/Build] Remove skip global cleanup in test_struct_output_generate.… pre-commit #154: Commit c7a29d2 pushed by benchislett
3m 24s main
main
3m 24s
[torchao] fix safetensors for sharding (#28169) pre-commit #153: Commit 1d64287 pushed by wangshangsam
3m 8s main
main
3m 8s
[Bugfix] Fix precision corruption when shared_experts_stream=None (#… pre-commit #152: Commit 9d2d561 pushed by benchislett
3m 41s main
main
3m 41s
Move online quantization to model.load_weights (#26327) pre-commit #151: Commit da94c7c pushed by wangshangsam
3m 34s main
main
3m 34s
Supress verbose logs from model_hosting_container_standards (#28949) pre-commit #150: Commit 67745d1 pushed by benchislett
3m 40s main
main
3m 40s
[Model][Perf] Use cos and sin cache in QwenVL (#28798) pre-commit #149: Commit b9489f5 pushed by vadiklyutiy
3m 32s main
main
3m 32s
Cast return value to int64_t for cache size (#28814) pre-commit #148: Commit e42bd8c pushed by vadiklyutiy
3m 33s main
main
3m 33s
[Bugfix] Fix ChunkedLocalAttention CUDA Graph setting (#28739) pre-commit #147: Commit bf3ffb6 pushed by wangshangsam
3m 29s main
main
3m 29s
[CI] Fix macos smoke test uv cache issue (#28736) pre-commit #146: Commit f08eab2 pushed by vadiklyutiy
3m 40s main
main
3m 40s
[CI] Bug: Fix ci entrypoint pooling (#28684) pre-commit #145: Commit e64011f pushed by wangshangsam
3m 29s main
main
3m 29s
Fix: Correctly filter special tokens in benchmark_prefix_caching (#28… pre-commit #144: Commit e63fd44 pushed by wangshangsam
3m 24s main
main
3m 24s
Skip models that cannot currently init on Transformers v5 (#28471) pre-commit #143: Commit 51c599f pushed by vadiklyutiy
3m 40s main
main
3m 40s
[Perf] Use np.ndarray instead of list[list[int]] to reduce GC overhea… pre-commit #142: Commit 4228be7 pushed by wangshangsam
3m 38s main
main
3m 38s
Remove weight_scale.T special case for SM90 Block FP8 CUTLASS kernel … pre-commit #141: Commit f9a4087 pushed by benchislett
3m 28s main
main
3m 28s
[Bugfix] Fix max image size for PaddleOCR-VL (#28442) pre-commit #140: Commit 4fd4b74 pushed by vadiklyutiy
3m 22s main
main
3m 22s
Bump starlette from 0.46.2 to 0.49.1 in /requirements pre-commit #139: Pull request #13 synchronize by dependabot bot
3m 48s dependabot/pip/requirements/starlette-0.49.1
dependabot/pip/requirements/starlette-0.49.1
3m 48s
Add @tjtanaa to codeowner for ROCm and multi-modal (#28360) pre-commit #138: Commit 4673e46 pushed by benchislett
4m 38s main
main
4m 38s
[Core] Rework handling of async scheduling config (#28250) pre-commit #137: Commit da786e3 pushed by vadiklyutiy
3m 56s main
main
3m 56s
[CPU]Improve cpu fused moe perf (#27244) pre-commit #136: Commit c757a15 pushed by vadiklyutiy
3m 25s main
main
3m 25s
[CI/Build] Fix test_defaults_with_usage_context in AMD CI (#27926) pre-commit #135: Commit 0b8e871 pushed by vadiklyutiy
3m 26s main
main
3m 26s