Skip to content

Actions: EmbeddedLLM/vllm

Actions

pre-commit

Actions

Loading...
Loading

Show workflow options

Create status badge

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

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
[Bugfix] Skip linear bias in layerwise reload to avoid corruption (#4… pre-commit #706: Commit 163ecba pushed by BadrBasowid
Pending main
main
Pending
[ROCm][CI] Prepare AMD mirrors for regating (#49270) pre-commit #705: Commit 1479bd9 pushed by BadrBasowid
Queued main
main
Queued
[CPU][Docs] Update docs and dockerfile for s390x (#49523) pre-commit #704: Commit f83de6d pushed by BadrBasowid
1d 0h 0m 2s main
main
1d 0h 0m 2s
[Spec Decode] Add kv_cache_dtype to speculative_config to control sep… pre-commit #703: Commit 8bfd683 pushed by vllmellm
1d 22h 43m 25s main
main
1d 22h 43m 25s
[ROCm][Bugfix] Enable the fp32 head_dtype torch.mm fast path on ROCm … pre-commit #702: Commit 7aab6e2 pushed by maralbahari
1d 19h 41m 12s main
main
1d 19h 41m 12s
[Bugfix] Set kv_quant_mode on the generic MLA KV-cache spec (#48379) pre-commit #701: Commit 6472131 pushed by BadrBasowid
1d 1h 3m 21s main
main
1d 1h 3m 21s
[Test] Enable KV cache events for HMA models in CPU offloading test (… pre-commit #700: Commit f04d3f6 pushed by maralbahari
18h 12m 4s main
main
18h 12m 4s
[Misc] Clean up "swap_space" (#48549) pre-commit #699: Commit 94c0ef3 pushed by BadrBasowid
1d 0h 0m 2s main
main
1d 0h 0m 2s
Mrv2dsv4 pre-commit #698: Pull request #86 opened by tjtanaa
1d 0h 0m 11s mrv2dsv4
mrv2dsv4
1d 0h 0m 11s
[ROCm] Enable DeepSeek-V4 DSpark speculative decoding on AMD (MI350X … pre-commit #697: Commit c227aaa pushed by tjtanaa
1d 10h 52m 31s main
main
1d 10h 52m 31s
Remove TeleChatForCausalLM (#47989) pre-commit #696: Commit ab7961a pushed by vllmellm
1d 19h 52m 47s main
main
1d 19h 52m 47s
[Bugfix][ROCm] Change AttentionCGSuppoort in TritonMLA to UNIFORM_SIN… pre-commit #695: Commit 2c17d33 pushed by BadrBasowid
1d 0h 0m 2s main
main
1d 0h 0m 2s
[Doc] Clarify fastokens availability (#45813) pre-commit #694: Commit 641cb59 pushed by tjtanaa
1d 15h 52m 48s main
main
1d 15h 52m 48s
[Test][XPU] Skip fork in kv_sharing_fast_prefill test on XPU (#47406) pre-commit #693: Commit 6971582 pushed by BadrBasowid
1d 0h 0m 1s main
main
1d 0h 0m 1s
[Bugfix] Fix CPU split-KV scratchpad sizing (#45844) pre-commit #692: Commit 26eb872 pushed by vllmellm
1d 0h 0m 2s main
main
1d 0h 0m 2s
[UX] Include NVTX in cuda.txt (#47319) pre-commit #691: Commit 1360c42 pushed by tjtanaa
1d 0h 56m 27s main
main
1d 0h 56m 27s
[XPU][UT]Enable ut qk_norm_rope_fusion (#42486) pre-commit #690: Commit f651a8a pushed by BadrBasowid
20h 11m 45s main
main
20h 11m 45s
[Bugfix] Raise VLLMValidationError for non-integer logit_bias keys (#… pre-commit #689: Commit 97b5ce5 pushed by vllmellm
1d 23h 8m 31s main
main
1d 23h 8m 31s
[Rust Frontend] Start current wave for a stale DP FirstRequest (#46833) pre-commit #688: Commit e45c8a9 pushed by BadrBasowid
1d 0h 0m 2s main
main
1d 0h 0m 2s
[Docs] Remove BambaForCausalLM from supported hybrid models list (#46… pre-commit #687: Commit bf292b5 pushed by tjtanaa
1d 21h 11m 49s main
main
1d 21h 11m 49s
[Bugfix] FLASHINFER_MLA_SPARSE_SM120 compatibility with GLM-5 NVFP4 (… pre-commit #686: Commit 8fa36fb pushed by tjtanaa
1d 13h 29m 57s main
main
1d 13h 29m 57s
[ROCm][CI] Expand basic correctness target suites (#46573) pre-commit #685: Commit 3f5a1e1 pushed by vllmellm
1d 0h 0m 2s main
main
1d 0h 0m 2s
[ROCm][P/D] Fix MoRIIO WRITE mode for mixed KV layouts (#46290) pre-commit #684: Commit 7e47fb7 pushed by tjtanaa
1d 21h 52m 27s main
main
1d 21h 52m 27s
[Doc] Fix typos, grammar, and broken commands across docs (#46398) pre-commit #683: Commit 33f5077 pushed by BadrBasowid
1d 0h 0m 2s main
main
1d 0h 0m 2s
Temporarily remove @markmc from CODEOWNERS (#46053) pre-commit #682: Commit bf2a393 pushed by tjtanaa
1d 14h 55m 28s main
main
1d 14h 55m 28s