Skip to content

Actions: vllm-project/vllm

Actions

pre-commit

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-commit.yml
64,135 workflow runs
64,135 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Bugfix] Fix Llama3JsonToolParser to support deeply nested JSON parameters pre-commit #64394: Pull request #28789 synchronize by ym820
3m 43s ym820:main
ym820:main
3m 43s
Enable bitsandbytes quantization on AMD GPUs that use warp size 32 pre-commit #64393: Pull request #27307 synchronize by sstamenk
3m 32s sstamenk:enable_bitsandbytes_quant_rocm
sstamenk:enable_bitsandbytes_quant_rocm
3m 32s
[Bugfix] Fix Llama3JsonToolParser to support deeply nested JSON parameters pre-commit #64392: Pull request #28789 synchronize by ym820
3m 25s ym820:main
ym820:main
3m 25s
Add INT4 compressed-tensors + LoRA support (including MoE) pre-commit #64391: Pull request #28791 synchronize by sheikheddy
3m 36s sheikheddy:feat/int4-compressed-tensors-lora-support
sheikheddy:feat/int4-compressed-tensors-lora-support
3m 36s
[Bugfix] Fix Llama3JsonToolParser to support deeply nested JSON parameters pre-commit #64390: Pull request #28789 synchronize by ym820
3m 13s ym820:main
ym820:main
3m 13s
Add INT4 compressed-tensors + LoRA support (including MoE) pre-commit #64389: Pull request #28791 synchronize by sheikheddy
3m 51s sheikheddy:feat/int4-compressed-tensors-lora-support
sheikheddy:feat/int4-compressed-tensors-lora-support
3m 51s
[2/n] parse reasoning item input in responses api pre-commit #64388: Pull request #28248 synchronize by qandrew
3m 35s qandrew:reasoning-item-input
qandrew:reasoning-item-input
3m 35s
Add INT4 compressed-tensors + LoRA support (including MoE) pre-commit #64387: Pull request #28791 synchronize by sheikheddy
2m 44s sheikheddy:feat/int4-compressed-tensors-lora-support
sheikheddy:feat/int4-compressed-tensors-lora-support
2m 44s
Add INT4 compressed-tensors + LoRA support (including MoE) pre-commit #64386: Pull request #28791 opened by sheikheddy
2m 59s sheikheddy:feat/int4-compressed-tensors-lora-support
sheikheddy:feat/int4-compressed-tensors-lora-support
2m 59s
[Bugfix] Fix Llama3JsonToolParser to support deeply nested JSON parameters pre-commit #64385: Pull request #28789 synchronize by ym820
3m 20s ym820:main
ym820:main
3m 20s
update test pre-commit #64384: Pull request #28695 synchronize by zhewenl
3m 24s zhewenl:add-llama4-fp8-amd-ci
zhewenl:add-llama4-fp8-amd-ci
3m 24s
[Perf] Optimize prompt logprobs loop iteration pre-commit #64383: Pull request #28790 opened by OthmanMohammad
3m 31s OthmanMohammad:perf-optimize-prompt-logprobs-loop
OthmanMohammad:perf-optimize-prompt-logprobs-loop
3m 31s
[Bugfix] Fix Llama3JsonToolParser to support deeply nested JSON parameters pre-commit #64382: Pull request #28789 opened by ym820
3m 19s ym820:main
ym820:main
3m 19s
[Build] Add OpenAI triton_kernels pre-commit #64381: Pull request #28788 opened by varun-sundar-rabindranath
3m 10s neuralmagic:varun/vendor-triton-kernels
neuralmagic:varun/vendor-triton-kernels
3m 10s
[BugFix] Fix `AssertionError: DCP not support reorder_batch_threshold… pre-commit #64380: Commit be263f7 pushed by LucasWilkinson
3m 6s main
main
3m 6s
[BugFix] Temporary fix for IMA with MTP = 2 and full-cg pre-commit #64379: Pull request #28315 synchronize by LucasWilkinson
3m 39s neuralmagic:lwilkinson/tmp-full-cg-mtp-2-fix
neuralmagic:lwilkinson/tmp-full-cg-mtp-2-fix
3m 39s
[BugFix] Fix async scheduling + chunked prefill + preemption pre-commit #64378: Pull request #28787 opened by njhill
3m 46s njhill:fix-async-preempt-chunkprefill
njhill:fix-async-preempt-chunkprefill
3m 46s
[Perf] Optimize multi-token incremental detokenization pre-commit #64377: Pull request #28786 opened by OthmanMohammad
3m 27s OthmanMohammad:perf-optimize-multi-token-detokenization
OthmanMohammad:perf-optimize-multi-token-detokenization
3m 27s
[BugFix] Temporary fix for IMA with MTP = 2 and full-cg pre-commit #64376: Pull request #28315 synchronize by LucasWilkinson
3m 44s neuralmagic:lwilkinson/tmp-full-cg-mtp-2-fix
neuralmagic:lwilkinson/tmp-full-cg-mtp-2-fix
3m 44s
[BugFix] Fix PP performance and PP kv connector output regression pre-commit #64375: Pull request #28768 synchronize by khluu
3m 54s njhill:fix-broken-pp
njhill:fix-broken-pp
3m 54s
[Doc]: fix typos in various files (#28567) pre-commit #64374: Commit 2bb4435 pushed by zhuohan123
3m 25s main
main
3m 25s
Update rope_scaling to rope_parameters in preparation for Transformers v5 pre-commit #64373: Pull request #28542 synchronize by hmellor
3m 27s hmellor:update-rope-config
hmellor:update-rope-config
3m 27s
[BugFix] Temporary fix for IMA with MTP = 2 and full-cg pre-commit #64372: Pull request #28315 synchronize by LucasWilkinson
3m 27s neuralmagic:lwilkinson/tmp-full-cg-mtp-2-fix
neuralmagic:lwilkinson/tmp-full-cg-mtp-2-fix
3m 27s
[Model][Qwen3VL] Cache positional embedding indices (#28475) pre-commit #64371: Commit 07cadab pushed by DarkLight1337
3m 29s main
main
3m 29s
docs: prefix caching seems quite outdated pre-commit #64370: Pull request #28784 opened by longregen
3m 28s longregen:patch-1
longregen:patch-1
3m 28s