Skip to content

Actions: CentML/vllm

Actions

pre-commit

Actions

Loading...
Loading

Show workflow options

Create status badge

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

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[BugFix][CPU] Fix x86 SHM distributed module initialization (#18536) pre-commit #16: Commit 93f7167 pushed by benchislett
6m 6s main
main
6m 6s
[Bugfix] Reduce moe_sum test size to avoid OOM (#18484) pre-commit #15: Commit c6c10ca pushed by benchislett
5m 49s main
main
5m 49s
[neuron] fix authorization issue (#18364) pre-commit #14: Commit d565e09 pushed by vadiklyutiy
5m 44s main
main
5m 44s
[V1][Spec Decode][Perf] Add fused Triton kernel to reduce overhead in EAGLE spec decoding pre-commit #13: Pull request #4 opened by leo-cf-tian
5m 51s eagle-kernel-fusion
eagle-kernel-fusion
5m 51s
[V1][Spec Decode] Share input embedding of target model with EAGLE dr… pre-commit #12: Commit 418d2f8 pushed by benchislett
7m 3s main
main
7m 3s
[Misc] remove --model from vllm serve usage (#17944) pre-commit #11: Commit 4c31218 pushed by xinli-sw
5m 49s main
main
5m 49s
[Bugfix] use_fast failing to be propagated to Qwen2-VL image proces… pre-commit #10: Commit 015815f pushed by benchislett
5m 29s main
main
5m 29s
[Quantization] Quark MXFP4 format loading (#16943) pre-commit #9: Commit db593aa pushed by benchislett
6m 35s main
main
6m 35s
[Kernel] some optimizations for dense marlin and moe marlin (#16850) pre-commit #8: Commit 1d0c9d6 pushed by benchislett
6m 18s main
main
6m 18s
[CI] Add automation for the tool-calling github label (#17118) pre-commit #7: Commit 4115f19 pushed by benchislett
5m 27s main
main
5m 27s
[V1][Spec Decode] Handle draft tokens beyond max_model_len (#16087) pre-commit #6: Commit 3a0fba5 pushed by benchislett
5m 31s main
main
5m 31s
[Doc] mention how to install in CPU editable mode (#16923) pre-commit #5: Commit f728ab8 pushed by benchislett
5m 16s main
main
5m 16s
[Doc] Document Matryoshka Representation Learning support (#16770) pre-commit #4: Commit 11c3b98 pushed by benchislett
6m 14s main
main
6m 14s
[Misc] Update usage with mooncake lib for kv transfer (#16523) pre-commit #3: Commit 1dd2338 pushed by benchislett
5m 28s main
main
5m 28s
[Kernel] support merge_attn_states CUDA kernel, 3x speedup (#16173) pre-commit #2: Commit e9528f6 pushed by benchislett
6m 8s main
main
6m 8s
Bump xgrammar from 0.1.16 to 0.1.18 in /requirements pre-commit #1: Pull request #3 opened by dependabot bot
6m 42s dependabot/pip/requirements/xgrammar-0.1.18
dependabot/pip/requirements/xgrammar-0.1.18
6m 42s