Skip to content

Actions: vllm-project/vllm

Actions

yapf

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
yapf.yml
29,608 workflow runs
29,608 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Model] PP support for Mamba-like models (#10992) yapf #30128: Commit ffa48c9 pushed by tlrmchlsmth
December 11, 2024 02:53 1m 47s main
main
December 11, 2024 02:53 1m 47s
[Bugfix] Fix Idefics3 fails during multi-image inference yapf #30127: Pull request #11080 opened by B-201
December 11, 2024 02:46 2m 20s B-201:fix-bug-idfics3-multi-image
B-201:fix-bug-idfics3-multi-image
December 11, 2024 02:46 2m 20s
[Hardware][CPU] support cpu in v1 engine yapf #30126: Pull request #11063 synchronize by yma11
December 11, 2024 02:26 1m 45s yma11:cpu-v1
yma11:cpu-v1
December 11, 2024 02:26 1m 45s
[Misc] LoRA + Chunked Prefill (#9057) yapf #30125: Commit d5c5154 pushed by jeejeelee
December 11, 2024 02:09 1m 43s main
main
December 11, 2024 02:09 1m 43s
[Core] V1: Use multiprocessing by default yapf #30124: Pull request #11074 reopened by robertgshaw2-neuralmagic
December 11, 2024 00:40 1m 46s russellb:v1-multiproc-by-default
russellb:v1-multiproc-by-default
December 11, 2024 00:40 1m 46s
[Frontend][Core] Add Guidance backend for guided decoding yapf #30123: Pull request #10217 synchronize by JC1DA
December 11, 2024 00:30 1m 48s JC1DA:support_guidance_logits_processor
JC1DA:support_guidance_logits_processor
December 11, 2024 00:30 1m 48s
[Bugfix] Fix Mamba multistep (#11071) yapf #30122: Commit 9a93973 pushed by tlrmchlsmth
December 11, 2024 00:16 1m 49s main
main
December 11, 2024 00:16 1m 49s
[V1] VLM preprocessor hashing yapf #30121: Pull request #11020 synchronize by alexm-neuralmagic
December 11, 2024 00:14 1m 47s v1_vlm_hash_mapper
v1_vlm_hash_mapper
December 11, 2024 00:14 1m 47s
[V1] VLM preprocessor hashing yapf #30120: Pull request #11020 synchronize by alexm-neuralmagic
December 11, 2024 00:13 1m 42s v1_vlm_hash_mapper
v1_vlm_hash_mapper
December 11, 2024 00:13 1m 42s
[Model] Add support for embedding model GritLM yapf #30119: Pull request #10816 synchronize by pooyadavoodi
December 10, 2024 23:38 1m 51s pooyadavoodi:add_gritlm_vllm
pooyadavoodi:add_gritlm_vllm
December 10, 2024 23:38 1m 51s
Tpu profiles yapf #30118: Pull request #11041 synchronize by robertgshaw2-neuralmagic
December 10, 2024 23:37 1m 50s neuralmagic:tpu-profiles
neuralmagic:tpu-profiles
December 10, 2024 23:37 1m 50s
[Model] Add support for embedding model GritLM yapf #30117: Pull request #10816 synchronize by pooyadavoodi
December 10, 2024 23:35 1m 42s pooyadavoodi:add_gritlm_vllm
pooyadavoodi:add_gritlm_vllm
December 10, 2024 23:35 1m 42s
[Core] v1: Use atexit to handle engine core client shutdown yapf #30116: Pull request #11076 opened by russellb
December 10, 2024 23:28 1m 44s russellb:v1-engine-client-shutdown
russellb:v1-engine-client-shutdown
December 10, 2024 23:28 1m 44s
[V1] Use input_ids as input for text-only models yapf #30115: Pull request #11032 synchronize by WoosukKwon
December 10, 2024 22:56 1m 51s v1-embedding-cg
v1-embedding-cg
December 10, 2024 22:56 1m 51s
[V1][Bugfix] Always set enable_chunked_prefill = True for V1 (#11061) yapf #30114: Commit 134810b pushed by WoosukKwon
December 10, 2024 22:41 1m 51s main
main
December 10, 2024 22:41 1m 51s
[Core] V1: Use multiprocessing by default yapf #30113: Pull request #11074 synchronize by russellb
December 10, 2024 22:27 1m 44s russellb:v1-multiproc-by-default
russellb:v1-multiproc-by-default
December 10, 2024 22:27 1m 44s
[Core] V1: Use multiprocessing by default yapf #30112: Pull request #11074 synchronize by russellb
December 10, 2024 22:16 2m 4s russellb:v1-multiproc-by-default
russellb:v1-multiproc-by-default
December 10, 2024 22:16 2m 4s
[Misc] add w8a8 asym models yapf #30111: Pull request #11075 opened by dsikka
December 10, 2024 22:13 1m 57s neuralmagic:update_w8a8_tests
neuralmagic:update_w8a8_tests
December 10, 2024 22:13 1m 57s
[torch.compile] Dynamic fp8 + rms_norm fusion yapf #30110: Pull request #10906 synchronize by ProExpertProg
December 10, 2024 22:02 2m 0s neuralmagic:luka/rms-norm-fusion-refactor
neuralmagic:luka/rms-norm-fusion-refactor
December 10, 2024 22:02 2m 0s
[Core] V1: Use multiprocessing by default yapf #30109: Pull request #11074 opened by russellb
December 10, 2024 21:50 1m 46s russellb:v1-multiproc-by-default
russellb:v1-multiproc-by-default
December 10, 2024 21:50 1m 46s
[Bugfix]: Clamp -inf logprob values in prompt_logprobs yapf #30108: Pull request #11073 synchronize by rafvasq
December 10, 2024 21:47 1m 52s rafvasq:investigate-top-k
rafvasq:investigate-top-k
December 10, 2024 21:47 1m 52s
[Bugfix]: Clamp -inf logprob values in prompt_logprobs yapf #30107: Pull request #11073 synchronize by rafvasq
December 10, 2024 21:46 1m 43s rafvasq:investigate-top-k
rafvasq:investigate-top-k
December 10, 2024 21:46 1m 43s
[Bugfix]: Clamp -inf logprob values in prompt_logprobs yapf #30106: Pull request #11073 opened by rafvasq
December 10, 2024 21:34 1m 47s rafvasq:investigate-top-k
rafvasq:investigate-top-k
December 10, 2024 21:34 1m 47s
[Bugfix] Fix Mamba multistep yapf #30105: Pull request #11071 opened by tlrmchlsmth
December 10, 2024 21:18 1m 49s neuralmagic:fix_mamba_multistep
neuralmagic:fix_mamba_multistep
December 10, 2024 21:18 1m 49s
[torch.compile] add a flag to track batchsize statistics (#11059) yapf #30104: Commit 75f89dc pushed by youkaichao
December 10, 2024 20:40 1m 49s main
main
December 10, 2024 20:40 1m 49s