karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 1 Packages Activity

[NVFP4][fix] Fix layer.weight -> w13 typo in NVFP4 MOE emulation kernel preparation (#41630)

Browse Source 
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
This commit is contained in:
fxmarty-amd
2026-05-04 20:13:37 +00:00
committed by GitHub
parent 844df54269
commit 9c07342fdc
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
vllm/model_executor/layers/fused_moe/oracle/nvfp4.py
+1 -1
View File
@@ -381,7 +381,7 @@ def convert_to_nvfp4_moe_kernel_format(
elif nvfp4_backend == NvFp4MoeBackend.EMULATION:
# Move the E2M1 lookup table to the device now, because
# `.to(device)` is not allowed during CUDA graph capture.
kE2M1ToFloat_handle.val = kE2M1ToFloat_handle.val.to(layer.weight.device)
kE2M1ToFloat_handle.val = kE2M1ToFloat_handle.val.to(w13.device)
if a13_scale is None or a2_scale is None:
raise ValueError(