Richard ZouandGitHub 3d64d366e0 [Misc] Change tests/compile to use VLLM_V1 by default (#19302) ...

Signed-off-by: rzou <zou3519@gmail.com>

2025-06-08 16:06:48 +08:00

..

__init__.py

[torch.compile] rework compile control with piecewise cudagraph (#9715)

2024-10-29 23:03:49 -07:00

test_full_cudagraph.py

[Bugfix] Fix FA3 full cuda graph correctness (#19106)

2025-06-03 23:10:15 -07:00

test_simple.py

[Misc] Change tests/compile to use VLLM_V1 by default (#19302)

2025-06-08 16:06:48 +08:00

test_toy_llama.py

[Bugfix] Re-enable use_cudagraph in vLLM v1 (#19299)

2025-06-08 08:56:12 +08:00