Skip to content

Fix Mistral Large 3 nightly test #25407

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

Merged
Fridge003 merged 1 commit into from
May 16, 2026
Merged

Fix Mistral Large 3 nightly test #25407

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions ...g/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -311,10 +311,10 @@ def apply_weights(
router_logits = topk_output.router_logits
topk_config = topk_output.topk_config

# Quantize input hidden states using fp4_quantize
# global_scale must be shape [1] (strict in cute-dsl backend).
hs_fp4_bytes, hs_sf_bytes = fp4_quantize(
x,
layer.w13_input_scale_quant,
layer.w13_input_scale_quant[:1],
Comment thread
b8zhong marked this conversation as resolved.
self.group_size, # sf_vec_size
False, # use_ue8m0
False, # is_sf_swizzled_layout
Expand Down
Loading