vllm/tests/compile/piecewise
Charlie Fu a44b1c951d
[Feature][ROCm] Add full graph capture support for TritonAttentionBackend (#19158)
Signed-off-by: charlifu <charlifu@amd.com>
2025-06-17 17:03:06 -04:00
..
__init__.py [torch.compile] rework compile control with piecewise cudagraph (#9715) 2024-10-29 23:03:49 -07:00
test_full_cudagraph.py [Feature][ROCm] Add full graph capture support for TritonAttentionBackend (#19158) 2025-06-17 17:03:06 -04:00
test_simple.py [CUDA] Enable full cudagraph for FlashMLA (#18581) 2025-06-13 18:12:26 +00:00
test_toy_llama.py [CUDA] Enable full cudagraph for FlashMLA (#18581) 2025-06-13 18:12:26 +00:00