Skip to content

[fix] Cherry pick "[TRTLLM-6262] Fix Llama4 Scout FP4 crash issue" #6267

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
merged 1 commit into from
Jul 23, 2025
Merged

[fix] Cherry pick "[TRTLLM-6262] Fix Llama4 Scout FP4 crash issue" #6267

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
5 changes: 5 additions & 0 deletions tensorrt_llm/_torch/models/modeling_llama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -159,15 +159,20 @@ def _forward_nope(
q = self._attention_scaling(q, position_ids)

out_scale = None
out_scale_sf = None
if self.o_proj.has_fp8_qdq or self.o_proj.has_nvfp4 or self.o_proj.has_fp8_block_scales:
out_scale = self.o_proj.inv_input_scale

if self.o_proj.has_nvfp4 and self.support_nvfp4_output:
out_scale_sf = self.o_proj.input_scale

q, k, v = self.convert_qkv(q, k, v)
attn_output = self.attn.forward(q,
k,
v,
attn_metadata,
out_scale=out_scale,
out_scale_sf=out_scale_sf,
attention_mask=attention_mask,
mrope_config=mrope_config)

Expand Down