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

changing config for fp8 gemm #3668

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
Changes from all commits
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
36 changes: 34 additions & 2 deletions fbgemm_gpu/experimental/gemm/triton_gemm/fp8_gemm.py
Original file line number Diff line number Diff line change
Expand Up @@ -2988,7 +2988,7 @@ def get_full_non_persistent_tuning_space():
# For now we see better perf with num_stages=0 for all gemm configs we care
# But keep this explicit so that we do not forget we may need to set it to
# other values in the future
num_stage_range = [0]
num_stage_range = [2]
waves_per_eu_range = [0]
matrix_instr_nonkdim_range = [16, 32]
kpack_range = [1, 2]
Expand Down Expand Up @@ -3025,7 +3025,39 @@ def get_full_non_persistent_tuning_space():
return configs


MATMUL_CONFIGS_NON_PERSISTENT: List[Config] = get_full_non_persistent_tuning_space()
MATMUL_CONFIGS_NON_PERSISTENT_4_8K_16K = [
triton.Config(
{
"BLOCK_M": 16,
"BLOCK_N": 16,
"BLOCK_K": 256,
"GROUP_M": 1,
"SPLIT_K": 1,
"waves_per_eu": 8,
"matrix_instr_nonkdim": 16,
"kpack": 2,
},
num_warps=2,
num_stages=2,
),
triton.Config(
{
"BLOCK_M": 16,
"BLOCK_N": 16,
"BLOCK_K": 256,
"GROUP_M": 1,
"SPLIT_K": 1,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2,
},
num_warps=2,
num_stages=2,
),
]

# MATMUL_CONFIGS_NON_PERSISTENT: List[Config] = get_full_non_persistent_tuning_space()
MATMUL_CONFIGS_NON_PERSISTENT = MATMUL_CONFIGS_NON_PERSISTENT_4_8K_16K


@triton.autotune(
Expand Down
Loading