forked from vllm-project/vllm
-
Notifications
You must be signed in to change notification settings - Fork 28
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
mixtral8x22B moe configs mi300 TP=1,2,4,8 (#277)
- Loading branch information
1 parent
3afc735
commit 04aa1a7
Showing
4 changed files
with
800 additions
and
0 deletions.
There are no files selected for viewing
200 changes: 200 additions & 0 deletions
200
...el_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X_OAM.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,200 @@ | ||
| { | ||
| "1": { | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 32, | ||
| "BLOCK_SIZE_K": 256, | ||
| "GROUP_SIZE_M": 1, | ||
| "num_warps": 2, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 2 | ||
| }, | ||
| "2": { | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 32, | ||
| "BLOCK_SIZE_K": 256, | ||
| "GROUP_SIZE_M": 1, | ||
| "num_warps": 1, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 2 | ||
| }, | ||
| "4": { | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 64, | ||
| "BLOCK_SIZE_K": 256, | ||
| "GROUP_SIZE_M": 1, | ||
| "num_warps": 4, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 2 | ||
| }, | ||
| "8": { | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 32, | ||
| "BLOCK_SIZE_K": 128, | ||
| "GROUP_SIZE_M": 1, | ||
| "num_warps": 2, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 2 | ||
| }, | ||
| "16": { | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 16, | ||
| "BLOCK_SIZE_K": 256, | ||
| "GROUP_SIZE_M": 1, | ||
| "num_warps": 1, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 2 | ||
| }, | ||
| "24": { | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 64, | ||
| "BLOCK_SIZE_K": 128, | ||
| "GROUP_SIZE_M": 1, | ||
| "num_warps": 4, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 1 | ||
| }, | ||
| "32": { | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 32, | ||
| "BLOCK_SIZE_K": 256, | ||
| "GROUP_SIZE_M": 4, | ||
| "num_warps": 2, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 2 | ||
| }, | ||
| "48": { | ||
| "BLOCK_SIZE_M": 32, | ||
| "BLOCK_SIZE_N": 32, | ||
| "BLOCK_SIZE_K": 256, | ||
| "GROUP_SIZE_M": 1, | ||
| "num_warps": 4, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 2 | ||
| }, | ||
| "64": { | ||
| "BLOCK_SIZE_M": 32, | ||
| "BLOCK_SIZE_N": 32, | ||
| "BLOCK_SIZE_K": 256, | ||
| "GROUP_SIZE_M": 4, | ||
| "num_warps": 4, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 2 | ||
| }, | ||
| "96": { | ||
| "BLOCK_SIZE_M": 32, | ||
| "BLOCK_SIZE_N": 32, | ||
| "BLOCK_SIZE_K": 256, | ||
| "GROUP_SIZE_M": 4, | ||
| "num_warps": 4, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 1 | ||
| }, | ||
| "128": { | ||
| "BLOCK_SIZE_M": 64, | ||
| "BLOCK_SIZE_N": 64, | ||
| "BLOCK_SIZE_K": 128, | ||
| "GROUP_SIZE_M": 4, | ||
| "num_warps": 8, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 1 | ||
| }, | ||
| "256": { | ||
| "BLOCK_SIZE_M": 128, | ||
| "BLOCK_SIZE_N": 128, | ||
| "BLOCK_SIZE_K": 64, | ||
| "GROUP_SIZE_M": 4, | ||
| "num_warps": 8, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 2 | ||
| }, | ||
| "512": { | ||
| "BLOCK_SIZE_M": 128, | ||
| "BLOCK_SIZE_N": 128, | ||
| "BLOCK_SIZE_K": 64, | ||
| "GROUP_SIZE_M": 1, | ||
| "num_warps": 2, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 2 | ||
| }, | ||
| "1024": { | ||
| "BLOCK_SIZE_M": 128, | ||
| "BLOCK_SIZE_N": 256, | ||
| "BLOCK_SIZE_K": 64, | ||
| "GROUP_SIZE_M": 1, | ||
| "num_warps": 8, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 1 | ||
| }, | ||
| "1536": { | ||
| "BLOCK_SIZE_M": 128, | ||
| "BLOCK_SIZE_N": 128, | ||
| "BLOCK_SIZE_K": 64, | ||
| "GROUP_SIZE_M": 4, | ||
| "num_warps": 8, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 2 | ||
| }, | ||
| "2048": { | ||
| "BLOCK_SIZE_M": 128, | ||
| "BLOCK_SIZE_N": 256, | ||
| "BLOCK_SIZE_K": 64, | ||
| "GROUP_SIZE_M": 1, | ||
| "num_warps": 8, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 2 | ||
| }, | ||
| "3072": { | ||
| "BLOCK_SIZE_M": 128, | ||
| "BLOCK_SIZE_N": 256, | ||
| "BLOCK_SIZE_K": 64, | ||
| "GROUP_SIZE_M": 1, | ||
| "num_warps": 8, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 1 | ||
| }, | ||
| "4096": { | ||
| "BLOCK_SIZE_M": 256, | ||
| "BLOCK_SIZE_N": 256, | ||
| "BLOCK_SIZE_K": 64, | ||
| "GROUP_SIZE_M": 1, | ||
| "num_warps": 8, | ||
| "num_stages": 0, | ||
| "waves_per_eu": 0, | ||
| "matrix_instr_nonkdim": 16, | ||
| "kpack": 2 | ||
| } | ||
| } |
Oops, something went wrong.