Skip to content

[#19362][fix] Name the act fusion in the skip reason #19448

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
100milliongold wants to merge 3 commits into
base: main
Choose a base branch
from
+6 −2
Open

[#19362][fix] Name the act fusion in the skip reason #19448

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9993a96
fix https://github.com/NVIDIA/TensorRT-LLM/issues/19362: name the act…
100milliongold Sep 20, 2026
eb66cfc
fix https://github.com/NVIDIA/TensorRT-LLM/issues/19362: name the MoE…
100milliongold Sep 25, 2026
abb4b19
fix https://github.com/NVIDIA/TensorRT-LLM/issues/19362: drop the MoE…
100milliongold Sep 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions tests/integration/defs/accuracy/test_llm_api_pytorch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1052,7 +1052,9 @@ def test_cute_dsl_nvfp4(
"""Test NVFP4 with CuTe DSL blockscaling mm (GEMM+SwiGLU fusion for shared experts)."""
sm_version = get_sm_version()
if sm_version not in (100, 103):
pytest.skip("CuTe DSL blockscaling mm supports SM 100 and 103 only")
pytest.skip(
"CuTe DSL NVFP4 GEMM+SwiGLU act fusion supports SM 100 and 103 only"
)

kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.9)
torch_compile_config = _get_default_torch_compile_config(torch_compile)
Expand Down Expand Up @@ -1104,7 +1106,9 @@ def test_cute_dsl_nvfp4_4gpus(
"""Test NVFP4 4 GPUs with CuTe DSL blockscaling mm (GEMM+SwiGLU fusion for shared experts)."""
sm_version = get_sm_version()
if sm_version not in (100, 103):
pytest.skip("CuTe DSL blockscaling mm supports SM 100 and 103 only")
pytest.skip(
"CuTe DSL NVFP4 GEMM+SwiGLU act fusion supports SM 100 and 103 only"
)

kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.9)
torch_compile_config = _get_default_torch_compile_config(torch_compile)
Expand Down
Loading