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

[Kernel] changing fused moe kernel chunk size default to 32k #7995

Merged
merged 1 commit into from
Aug 30, 2024
Merged

[Kernel] changing fused moe kernel chunk size default to 32k #7995

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
changing fused moe kernel chunk size default to 32k
  • Loading branch information
@avshalomman
avshalomman committed Aug 29, 2024
commit 989e2e62dee691b1eb4e715232c9d97ed54c96a0
2 changes: 1 addition & 1 deletion vllm/envs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -352,7 +352,7 @@ def get_default_config_root():
os.path.join(get_default_cache_root(), "vllm", "xla_cache"),
)),
"VLLM_FUSED_MOE_CHUNK_SIZE":
lambda: int(os.getenv("VLLM_FUSED_MOE_CHUNK_SIZE", "65536")),
lambda: int(os.getenv("VLLM_FUSED_MOE_CHUNK_SIZE", "32768")),

# If set, vllm will skip the deprecation warnings.
"VLLM_NO_DEPRECATION_WARNING":
Expand Down
Loading