Fix fp8_attention

pytorch-labs · Nov 19, 2024 · a67aa88 · a67aa88
1 parent 850ec97
commit a67aa88
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/test/test_gpu/skip_tests_h100_pytorch.yaml b/test/test_gpu/skip_tests_h100_pytorch.yaml
@@ -17,6 +17,9 @@ flash_attention:
 #   - flex_attention
 fp8_attention:
   - colfax_fmha
+  # triton_flash_v2 now requires the main branch of Triton
+  # pytorch version does not work
+  - triton_flash_v2
 fp8_fused_quant_gemm_rowwise:
 fp8_gemm:
   - triton_persistent_fp8_gemm