A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
support flashinfer_fp4 moe for 5090 gpu (#26669)
Signed-off-by: XiaobingSuper <xiaobingzhangupc@gmail.com> Signed-off-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Michael Goin <mgoin64@gmail.com>
XiaobingZhang committed
Oct 16, 2025 at 03:06 UTC
0b99f5d3023a84f120e6af7df355824e0f39af93
1 file changed
+1
-1
vllm/model_executor/layers/quantization/utils/flashinfer_fp4_moe.py
+1
-1
@@ -32,7 +32,7 @@ def is_flashinfer_fp4_cutlass_moe_available() -> bool:
32
envs.VLLM_USE_FLASHINFER_MOE_FP4
33
and has_flashinfer_cutlass_fused_moe()
34
and current_platform.is_cuda()
35
- and current_platform.is_device_capability(100)
35
+ and current_platform.has_device_capability(100)
36
)
37
38