iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix][Transformers backend] Fix CUDA graph capture for dynamic-rope models (#58064)

Browse Source 
Signed-off-by: YongfengX <erkang040804@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
This commit is contained in:
Frank
2026-10-14 05:56:54 -07:00
committed by GitHub
co-authored by Claude Opus 5 Harry Mellor Kevin H. Luu
parent 2631afd3fe
commit 3723a1ea96
4 changed files with 132 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.buildkite/test_areas/models_basic.yaml
+2 -1
View File
@@ -253,6 +253,7 @@ steps:
- tests/models/test_adapters.py
- tests/models/test_qwen3_5_mtp_config.py
- tests/models/transformers/fusers/
- tests/models/transformers/test_dynamic_rope.py
- tests/model_executor/layers/test_activation.py
- tests/models/test_language_model_cache_is_weak.py
- tests/models/deepseek_v32/test_sequence_parallel.py
@@ -261,7 +262,7 @@ steps:
- tests/models/transformers/test_layer_registry.py
device: cpu-small
commands:
- pytest -v -s models/test_utils.py models/test_vision.py models/test_adapters.py models/test_qwen3_5_mtp_config.py models/transformers/fusers/ model_executor/layers/test_activation.py models/test_language_model_cache_is_weak.py models/deepseek_v32/test_sequence_parallel.py models/test_deepseek_v4_fi_moe_ep.py models/test_dspark_mla.py models/transformers/test_layer_registry.py
- pytest -v -s models/test_utils.py models/test_vision.py models/test_adapters.py models/test_qwen3_5_mtp_config.py models/transformers/fusers/ models/transformers/test_dynamic_rope.py model_executor/layers/test_activation.py models/test_language_model_cache_is_weak.py models/deepseek_v32/test_sequence_parallel.py models/test_deepseek_v4_fi_moe_ep.py models/test_dspark_mla.py models/transformers/test_layer_registry.py
- label: ':amd: (MI355) DeepSeek-V4.1 Mono Decode Numerics'
key: dsv41-mono-decode-numerics-amd