Skip to content

[Bugfix] Fix benchmark_moe.py #19016

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.

Sign up for GitHub

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

Merged
merged 4 commits into from
Jun 10, 2025
Merged

[Bugfix] Fix benchmark_moe.py #19016

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e6bfa19
Fix benchmark_moe.py
gty111 Jun 2, 2025
f2a7a54
Fix pre-commit on bechmark_moe.py
gty111 Jun 2, 2025
b643d78
Update benchmark_moe.py
gty111 Jun 7, 2025
e3b623d
Using list instead of List
gty111 Jun 7, 2025
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
14 changes: 4 additions & 10 deletions benchmarks/kernels/benchmark_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,6 @@
from contextlib import nullcontext
from datetime import datetime
from itertools import product
from types import SimpleNamespace
from typing import Any, TypedDict

import ray
Expand Down Expand Up @@ -42,7 +41,7 @@ def benchmark_config(
use_fp8_w8a8: bool,
use_int8_w8a16: bool,
num_iters: int = 100,
block_quant_shape: List[int] = None,
block_quant_shape: list[int] = None,
use_deep_gemm: bool = False,
) -> float:
init_dtype = torch.float16 if use_fp8_w8a8 else dtype
Expand Down Expand Up @@ -399,7 +398,7 @@ def benchmark(
dtype: torch.dtype,
use_fp8_w8a8: bool,
use_int8_w8a16: bool,
block_quant_shape: List[int] = None,
block_quant_shape: list[int] = None,
use_deep_gemm: bool = False,
) -> tuple[dict[str, int], float]:
current_platform.seed_everything(self.seed)
Expand Down Expand Up @@ -531,7 +530,7 @@ def save_configs(
dtype: torch.dtype,
use_fp8_w8a8: bool,
use_int8_w8a16: bool,
block_quant_shape: List[int],
block_quant_shape: list[int],
) -> None:
dtype_str = get_config_dtype_str(
dtype, use_int8_w8a16=use_int8_w8a16, use_fp8_w8a8=use_fp8_w8a8
Expand Down Expand Up @@ -562,7 +561,6 @@ def main(args: argparse.Namespace):
config = get_config(model=args.model, trust_remote_code=args.trust_remote_code)
if args.model_prefix:
config = getattr(config, args.model_prefix)
config = SimpleNamespace(**config)

if config.architectures[0] == "DbrxForCausalLM":
E = config.ffn_config.moe_num_experts
Expand Down Expand Up @@ -594,11 +592,7 @@ def main(args: argparse.Namespace):
shard_intermediate_size = 2 * intermediate_size // args.tp_size

hidden_size = config.hidden_size
dtype = (
torch.float16
if current_platform.is_rocm()
else getattr(torch, config.torch_dtype)
)
dtype = torch.float16 if current_platform.is_rocm() else config.torch_dtype
use_fp8_w8a8 = args.dtype == "fp8_w8a8"
use_int8_w8a16 = args.dtype == "int8_w8a16"
block_quant_shape = get_weight_block_size_safety(config)
Expand Down