mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2026-05-03 20:04:41 +08:00
[ROCm][MoE] mi300 mixtral8x7B perf for specific BS (#13577)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
This commit is contained in:
parent
88f6ba3281
commit
0d243f2a54
@ -45,8 +45,8 @@
|
|||||||
},
|
},
|
||||||
"16": {
|
"16": {
|
||||||
"BLOCK_SIZE_M": 16,
|
"BLOCK_SIZE_M": 16,
|
||||||
"BLOCK_SIZE_N": 16,
|
"BLOCK_SIZE_N": 64,
|
||||||
"BLOCK_SIZE_K": 256,
|
"BLOCK_SIZE_K": 64,
|
||||||
"GROUP_SIZE_M": 1,
|
"GROUP_SIZE_M": 1,
|
||||||
"num_warps": 2,
|
"num_warps": 2,
|
||||||
"num_stages": 2,
|
"num_stages": 2,
|
||||||
|
|||||||
@ -45,8 +45,8 @@
|
|||||||
},
|
},
|
||||||
"16": {
|
"16": {
|
||||||
"BLOCK_SIZE_M": 16,
|
"BLOCK_SIZE_M": 16,
|
||||||
"BLOCK_SIZE_N": 32,
|
"BLOCK_SIZE_N": 64,
|
||||||
"BLOCK_SIZE_K": 256,
|
"BLOCK_SIZE_K": 128,
|
||||||
"GROUP_SIZE_M": 1,
|
"GROUP_SIZE_M": 1,
|
||||||
"num_warps": 2,
|
"num_warps": 2,
|
||||||
"num_stages": 2,
|
"num_stages": 2,
|
||||||
|
|||||||
@ -128,7 +128,7 @@
|
|||||||
"num_warps": 8,
|
"num_warps": 8,
|
||||||
"num_stages": 2,
|
"num_stages": 2,
|
||||||
"waves_per_eu": 0,
|
"waves_per_eu": 0,
|
||||||
"matrix_instr_nonkdim": 32,
|
"matrix_instr_nonkdim": 16,
|
||||||
"kpack": 2
|
"kpack": 2
|
||||||
},
|
},
|
||||||
"512": {
|
"512": {
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user