mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2026-05-25 15:37:59 +08:00
[Hardware][AMD][Model] Triton MoE tuning configs for GLM-4.6 for MI300X (#27323)
Signed-off-by: minatoaquaMK2 <jiacheng.yue@foxmail.com>
This commit is contained in:
parent
5b3c35a68e
commit
bdb01a38fe
@ -0,0 +1,201 @@
|
|||||||
|
{
|
||||||
|
"triton_version": "3.4.0",
|
||||||
|
"1": {
|
||||||
|
"BLOCK_SIZE_M": 16,
|
||||||
|
"BLOCK_SIZE_N": 16,
|
||||||
|
"BLOCK_SIZE_K": 256,
|
||||||
|
"GROUP_SIZE_M": 1,
|
||||||
|
"num_warps": 4,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
},
|
||||||
|
"2": {
|
||||||
|
"BLOCK_SIZE_M": 16,
|
||||||
|
"BLOCK_SIZE_N": 64,
|
||||||
|
"BLOCK_SIZE_K": 128,
|
||||||
|
"GROUP_SIZE_M": 1,
|
||||||
|
"num_warps": 4,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
},
|
||||||
|
"4": {
|
||||||
|
"BLOCK_SIZE_M": 16,
|
||||||
|
"BLOCK_SIZE_N": 64,
|
||||||
|
"BLOCK_SIZE_K": 128,
|
||||||
|
"GROUP_SIZE_M": 1,
|
||||||
|
"num_warps": 4,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
},
|
||||||
|
"8": {
|
||||||
|
"BLOCK_SIZE_M": 16,
|
||||||
|
"BLOCK_SIZE_N": 64,
|
||||||
|
"BLOCK_SIZE_K": 128,
|
||||||
|
"GROUP_SIZE_M": 1,
|
||||||
|
"num_warps": 4,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 1
|
||||||
|
},
|
||||||
|
"16": {
|
||||||
|
"BLOCK_SIZE_M": 16,
|
||||||
|
"BLOCK_SIZE_N": 64,
|
||||||
|
"BLOCK_SIZE_K": 64,
|
||||||
|
"GROUP_SIZE_M": 4,
|
||||||
|
"num_warps": 4,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
},
|
||||||
|
"24": {
|
||||||
|
"BLOCK_SIZE_M": 16,
|
||||||
|
"BLOCK_SIZE_N": 32,
|
||||||
|
"BLOCK_SIZE_K": 64,
|
||||||
|
"GROUP_SIZE_M": 1,
|
||||||
|
"num_warps": 1,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
},
|
||||||
|
"32": {
|
||||||
|
"BLOCK_SIZE_M": 16,
|
||||||
|
"BLOCK_SIZE_N": 64,
|
||||||
|
"BLOCK_SIZE_K": 128,
|
||||||
|
"GROUP_SIZE_M": 4,
|
||||||
|
"num_warps": 2,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
},
|
||||||
|
"48": {
|
||||||
|
"BLOCK_SIZE_M": 16,
|
||||||
|
"BLOCK_SIZE_N": 64,
|
||||||
|
"BLOCK_SIZE_K": 64,
|
||||||
|
"GROUP_SIZE_M": 8,
|
||||||
|
"num_warps": 1,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
},
|
||||||
|
"64": {
|
||||||
|
"BLOCK_SIZE_M": 16,
|
||||||
|
"BLOCK_SIZE_N": 128,
|
||||||
|
"BLOCK_SIZE_K": 64,
|
||||||
|
"GROUP_SIZE_M": 4,
|
||||||
|
"num_warps": 8,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
},
|
||||||
|
"96": {
|
||||||
|
"BLOCK_SIZE_M": 16,
|
||||||
|
"BLOCK_SIZE_N": 128,
|
||||||
|
"BLOCK_SIZE_K": 64,
|
||||||
|
"GROUP_SIZE_M": 32,
|
||||||
|
"num_warps": 8,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 1
|
||||||
|
},
|
||||||
|
"128": {
|
||||||
|
"BLOCK_SIZE_M": 16,
|
||||||
|
"BLOCK_SIZE_N": 128,
|
||||||
|
"BLOCK_SIZE_K": 64,
|
||||||
|
"GROUP_SIZE_M": 16,
|
||||||
|
"num_warps": 8,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
},
|
||||||
|
"256": {
|
||||||
|
"BLOCK_SIZE_M": 16,
|
||||||
|
"BLOCK_SIZE_N": 128,
|
||||||
|
"BLOCK_SIZE_K": 64,
|
||||||
|
"GROUP_SIZE_M": 32,
|
||||||
|
"num_warps": 8,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
},
|
||||||
|
"512": {
|
||||||
|
"BLOCK_SIZE_M": 32,
|
||||||
|
"BLOCK_SIZE_N": 128,
|
||||||
|
"BLOCK_SIZE_K": 64,
|
||||||
|
"GROUP_SIZE_M": 32,
|
||||||
|
"num_warps": 4,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 1
|
||||||
|
},
|
||||||
|
"1024": {
|
||||||
|
"BLOCK_SIZE_M": 64,
|
||||||
|
"BLOCK_SIZE_N": 128,
|
||||||
|
"BLOCK_SIZE_K": 64,
|
||||||
|
"GROUP_SIZE_M": 4,
|
||||||
|
"num_warps": 8,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
},
|
||||||
|
"1536": {
|
||||||
|
"BLOCK_SIZE_M": 128,
|
||||||
|
"BLOCK_SIZE_N": 128,
|
||||||
|
"BLOCK_SIZE_K": 64,
|
||||||
|
"GROUP_SIZE_M": 16,
|
||||||
|
"num_warps": 4,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
},
|
||||||
|
"2048": {
|
||||||
|
"BLOCK_SIZE_M": 128,
|
||||||
|
"BLOCK_SIZE_N": 128,
|
||||||
|
"BLOCK_SIZE_K": 64,
|
||||||
|
"GROUP_SIZE_M": 4,
|
||||||
|
"num_warps": 8,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 1
|
||||||
|
},
|
||||||
|
"3072": {
|
||||||
|
"BLOCK_SIZE_M": 256,
|
||||||
|
"BLOCK_SIZE_N": 128,
|
||||||
|
"BLOCK_SIZE_K": 64,
|
||||||
|
"GROUP_SIZE_M": 32,
|
||||||
|
"num_warps": 8,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
},
|
||||||
|
"4096": {
|
||||||
|
"BLOCK_SIZE_M": 256,
|
||||||
|
"BLOCK_SIZE_N": 128,
|
||||||
|
"BLOCK_SIZE_K": 64,
|
||||||
|
"GROUP_SIZE_M": 16,
|
||||||
|
"num_warps": 8,
|
||||||
|
"num_stages": 2,
|
||||||
|
"waves_per_eu": 0,
|
||||||
|
"matrix_instr_nonkdim": 16,
|
||||||
|
"kpack": 2
|
||||||
|
}
|
||||||
|
}
|
||||||
Loading…
x
Reference in New Issue
Block a user