Skip to content
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

Fix glm4 error #12474

Merged
merged 1 commit into from
Dec 2, 2024
Merged

Fix glm4 error #12474

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: 1 addition & 3 deletions python/llm/src/ipex_llm/vllm/xpu/model_convert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,9 +94,7 @@ def _ipex_llm_load_model(self) -> None:
from ipex_llm import optimize_model
import os
not_convert_last_mlp = os.getenv("IPEX_LLM_NOT_CONVERT_LAST_MLP", None)
is_glm4_model = "glm-4" in self.model_config.model.lower()
is_codegeex4_model = "codegeex4-all" in self.model_config.model.lower()
if not_convert_last_mlp is not None or is_glm4_model or is_codegeex4_model:
if not_convert_last_mlp is not None:
# only use to avoid nan value in last mlp forward running glm4-9b-chat
modules = ["35.mlp", "36.mlp", "37.mlp", "38.mlp", "39.mlp"]
else:
Expand Down