This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
Files
be95edb7f6820ff6b341e6e48ba7bfa15d628209
vLLM
/
tests
/
v1
/
cudagraph
T
History
MOVZX
be95edb7f6
Merge branch 'main' into patches
...
Signed-off-by: MOVZX <
movzx@yahoo.com
>
2026-10-16 17:35:42 +07:00
..
__init__.py
[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (
#20059
)
2025-08-15 10:01:39 -04:00
test_breakable_cudagraph.py
[XPU][CI] Enable XPU graph in graph tests (
#60784
)
2026-10-12 10:39:40 +08:00
test_cudagraph_dispatch.py
[Attention] Remove cascade attention (
#61126
)
2026-10-12 10:41:07 -07:00
test_cudagraph_manager.py
Merge branch 'main' into patches
2026-10-15 21:16:39 +07:00
test_cudagraph_mode.py
[XPU][CI] Enable XPU graph in graph tests (
#60784
)
2026-10-12 10:39:40 +08:00
test_encoder_cudagraph.py
[MM][CG] Support ViT full CUDA graph for DeepSeek-VL2 (
#46005
)
2026-10-15 21:38:52 +08:00