Skip to content

Actions: ji-huazhong/vllm

yapf

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
23 workflow runs
23 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Bugfix] Set enforce_eager automatically for mllama (#12127)
yapf #23: Commit d06e824 pushed by ji-huazhong
January 17, 2025 00:24 2m 8s main
January 17, 2025 00:24 2m 8s
January 16, 2025 00:22 2m 20s
Misc: allow to use proxy in HTTPConnection (#12042)
yapf #21: Commit 5ecf3e0 pushed by ji-huazhong
January 15, 2025 15:28 2m 5s main
January 15, 2025 15:28 2m 5s
[Platform] move current_memory_usage() into platform (#11369)
yapf #20: Commit 9ddac56 pushed by ji-huazhong
January 15, 2025 03:59 2m 8s main
January 15, 2025 03:59 2m 8s
[Kernel] Support MulAndSilu (#11624)
yapf #19: Commit 42f5e7c pushed by ji-huazhong
January 15, 2025 02:30 2m 6s main
January 15, 2025 02:30 2m 6s
January 15, 2025 00:07 2m 12s
[Platform] Add output for Attention Backend (#11981)
yapf #17: Commit 2e0e017 pushed by ji-huazhong
January 14, 2025 15:12 2m 24s main
January 14, 2025 15:12 2m 24s
January 10, 2025 14:31 1m 56s
November 24, 2024 05:01 1m 57s
[Platforms] Refactor openvino code
yapf #14: Commit 865339e pushed by ji-huazhong
November 22, 2024 12:03 1m 51s main
November 22, 2024 12:03 1m 51s
Remove token-adding chat embedding params (#10551)
yapf #13: Commit 11fcf0e pushed by ji-huazhong
November 22, 2024 11:20 2m 45s main
November 22, 2024 11:20 2m 45s
November 22, 2024 06:10 1m 58s
[Misc] Support quantization of MllamaForCausalLM (#8822)
yapf #11: Commit 7193774 pushed by ji-huazhong
September 26, 2024 09:19 2m 30s main
September 26, 2024 09:19 2m 30s
[Misc] Fix minor typo in scheduler (#8765)
yapf #10: Commit 8fae5ed pushed by ji-huazhong
September 25, 2024 13:37 2m 28s main
September 25, 2024 13:37 2m 28s
[Hardware][CPU] Refactor CPU model runner (#8729)
yapf #9: Commit e551ca1 pushed by ji-huazhong
September 23, 2024 12:35 2m 19s main
September 23, 2024 12:35 2m 19s
[Bugfix] Refactor composite weight loading logic (#8656)
yapf #8: Commit 13d88d4 pushed by ji-huazhong
September 22, 2024 05:51 2m 18s main
September 22, 2024 05:51 2m 18s
[MISC] remove engine_use_ray in benchmark_throughput.py (#8615)
yapf #7: Commit 855c8ae pushed by ji-huazhong
September 19, 2024 10:19 2m 14s main
September 19, 2024 10:19 2m 14s
[Misc] Use RoPE cache for MRoPE (#8396)
yapf #6: Commit 42ffba1 pushed by ji-huazhong
September 12, 2024 06:54 2m 15s main
September 12, 2024 06:54 2m 15s
[Misc] Skip loading extra bias for Qwen2-MOE GPTQ models (#8329)
yapf #5: Commit e497b8a pushed by ji-huazhong
September 11, 2024 01:19 2m 12s main
September 11, 2024 01:19 2m 12s
[Bugfix] Fix missing post_layernorm in CLIP (#8155)
yapf #4: Commit da1a844 pushed by ji-huazhong
September 10, 2024 09:15 2m 8s main
September 10, 2024 09:15 2m 8s
[Misc]: optimize eager mode host time (#4196)
yapf #3: Commit a377f0b pushed by ji-huazhong
May 31, 2024 08:20 1m 22s main
May 31, 2024 08:20 1m 22s
May 31, 2024 01:01 3m 44s
[Misc] Make Serving Benchmark More User-friendly (#5044)
yapf #1: Commit f17a1a8 pushed by ji-huazhong
May 27, 2024 04:53 1m 8s main
May 27, 2024 04:53 1m 8s