Skip to content

Actions: triple-Mu/vllm_official

clang-format

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
231 workflow runs
231 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Frontend] re-enable multi-modality input in the new beam search impl…
clang-format #206: Commit ef7865b pushed by triple-Mu
October 29, 2024 11:58 18s main
October 29, 2024 11:58 18s
[Bugfix] Fix ray instance detect issue (#9439)
clang-format #205: Commit 2adb440 pushed by triple-Mu
October 28, 2024 14:24 19s main
October 28, 2024 14:24 19s
[Misc] Upgrade to pytorch 2.5 (#9588)
clang-format #204: Commit 3cb07a3 pushed by triple-Mu
October 27, 2024 12:12 16s main
October 27, 2024 12:12 16s
[V1] Support sliding window attention (#9679)
clang-format #203: Commit 9645b9f pushed by triple-Mu
October 25, 2024 11:59 18s main
October 25, 2024 11:59 18s
[CI/Build] Split up decoder-only LM tests (#9488)
clang-format #202: Commit 696b01a pushed by triple-Mu
October 21, 2024 14:25 19s main
October 21, 2024 14:25 19s
[Model] Molmo vLLM Integration (#9016)
clang-format #201: Commit dfe43a2 pushed by triple-Mu
October 14, 2024 15:05 21s main
October 14, 2024 15:05 21s
[Bugfix] Bandaid fix for speculative decoding tests (#9327)
clang-format #200: Commit 16b24e7 pushed by triple-Mu
October 14, 2024 14:31 14s main
October 14, 2024 14:31 14s
[CI] Fix merge conflict (#9317)
clang-format #199: Commit f519902 pushed by triple-Mu
October 13, 2024 11:46 37s main
October 13, 2024 11:46 37s
[Bugfix] Fix bug of xformer prefill for encoder-decoder (#9026)
clang-format #198: Commit 00298e0 pushed by triple-Mu
October 12, 2024 14:59 15s main
October 12, 2024 14:59 15s
[BugFix] Fix tool call finish reason in streaming case (#9209)
clang-format #197: Commit ec10cb8 pushed by triple-Mu
October 12, 2024 04:16 19s main
October 12, 2024 04:16 19s
[Misc][LoRA] Support loading LoRA weights for target_modules in reg f…
clang-format #196: Commit 36ea790 pushed by triple-Mu
October 11, 2024 13:25 26s main
October 11, 2024 13:25 26s
[misc] hide best_of from engine (#9261)
clang-format #195: Commit cbc2ef5 pushed by triple-Mu
October 11, 2024 07:04 20s main
October 11, 2024 07:04 20s
Add classifiers in setup.py (#9171)
clang-format #194: Commit ffc4b27 pushed by triple-Mu
October 9, 2024 03:22 22s main
October 9, 2024 03:22 22s
[Frontend] API support for beam search for MQLLMEngine (#9117)
clang-format #193: Commit 8c74622 pushed by triple-Mu
October 8, 2024 13:37 19s main
October 8, 2024 13:37 19s
[Model] Support NVLM-D and fix QK Norm in InternViT (#9045)
clang-format #192: Commit 151ef4e pushed by triple-Mu
October 7, 2024 12:27 14s main
October 7, 2024 12:27 14s
[Core] [Frontend] Priority scheduling for embeddings and in the OpenA…
clang-format #191: Commit 35bd215 pushed by triple-Mu
October 1, 2024 13:55 20s main
October 1, 2024 13:55 20s
[Misc] Adjust max_position_embeddings for LoRA compatibility (#8957)
clang-format #190: Commit 1cabfce pushed by triple-Mu
September 30, 2024 14:18 17s main
September 30, 2024 14:18 17s
[Model] support input embeddings for qwen2vl (#8856)
clang-format #189: Commit e01ab59 pushed by triple-Mu
September 30, 2024 03:20 22s main
September 30, 2024 03:20 22s
[BugFix] Fix seeded random sampling with encoder-decoder models (#8870)
clang-format #188: Commit 31f46a0 pushed by triple-Mu
September 29, 2024 12:09 15s main
September 29, 2024 12:09 15s
[Bugfix] Fix Marlin MoE act order when is_k_full == False (#8741)
clang-format #187: Commit d081da0 pushed by triple-Mu
September 29, 2024 02:29 18s main
September 29, 2024 02:29 18s
[Bugfix] Fix code for downloading models from modelscope (#8443)
clang-format #186: Commit 39d3f8d pushed by triple-Mu
September 28, 2024 15:36 15s main
September 28, 2024 15:36 15s
[Misc] Remove vLLM patch of BaichuanTokenizer (#8921)
clang-format #185: Commit b0298aa pushed by triple-Mu
September 28, 2024 13:11 16s main
September 28, 2024 13:11 16s
[Bugfix][Intel] Fix XPU Dockerfile Build (#7824)
clang-format #184: Commit 260024a pushed by triple-Mu
September 28, 2024 07:25 13s main
September 28, 2024 07:25 13s
[TPU] Update pallas.py to support trillium (#8871)
clang-format #183: Commit 8df2dc3 pushed by triple-Mu
September 27, 2024 11:26 19s main
September 27, 2024 11:26 19s
[Misc] Support quantization of MllamaForCausalLM (#8822)
clang-format #182: Commit 7193774 pushed by triple-Mu
September 26, 2024 02:03 16s main
September 26, 2024 02:03 16s