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.

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

Fused MOE for Mixtral #2542

Merged
merged 23 commits into from
Jan 30, 2024
Merged
Changes from 1 commit
Commits
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
Prev Previous commit
Next Next commit
optimize block sizes
  • Loading branch information
pcmoritz committed Jan 24, 2024
commit adeb80f2ae0b82cbd3bc9b3476d1868ffbc8f4fc
6 changes: 3 additions & 3 deletions vllm/model_executor/layers/fused_moe.py
Original file line number Diff line number Diff line change
Expand Up @@ -198,9 +198,9 @@ def fused_moe(hidden_states: torch.Tensor,
E, N, K = w1.shape

config = {
'BLOCK_SIZE_M': 64,
'BLOCK_SIZE_N': 64,
'BLOCK_SIZE_K': 32,
'BLOCK_SIZE_M': 128,
'BLOCK_SIZE_N': 128,
'BLOCK_SIZE_K': 64,
'GROUP_SIZE_M': 8
}

Expand Down
Loading