biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Feature] Add SM103 (Blackwell Ultra) Support to vLLM (#30484)

Browse Source 
Signed-off-by: LopezCastroRoberto <robertol.c510@gmail.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
Roberto L. Castro
2025-12-13 04:34:23 +01:00
committed by GitHub
parent 57e9bf1864
commit 4fa7ce46f3
21 changed files with 53 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/kernels/moe/test_ocp_mx_moe.py
View File

@@ -17,7 +17,7 @@ QUARK_MXFP4_AVAILABLE = find_spec("quark") is not None and version.parse(
) >= version.parse("0.8.99")
TRTLLM_GEN_MXFP4_AVAILABLE = (
current_platform.is_cuda() and current_platform.is_device_capability(100)
current_platform.is_cuda() and current_platform.is_device_capability_family(100)
)
HOPPER_MXFP4_BF16_AVAILABLE = (
@@ -799,7 +799,7 @@ def test_flashinfer_cutlass_mxfp4_fused_moe(
@pytest.mark.skipif(
not (
current_platform.is_cuda()
and current_platform.is_device_capability(100)
and current_platform.is_device_capability_family(100)
and has_flashinfer()
),
reason="NVIDIA GPU sm100 and flashinfer are required for this test",