biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Refactor] Remove moe_align_block_size_triton (#21335)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye
2025-07-26 10:08:29 -04:00
committed by GitHub
parent 97d6c30cc9
commit 56e544f24b
2 changed files with 6 additions and 224 deletions
Download Patch File Download Diff File Expand all files Collapse all files

90
benchmarks/kernels/benchmark_moe_align_block_size.py
View File

@@ -5,9 +5,8 @@ import itertools
import torch
from vllm import _custom_ops as ops
from vllm.model_executor.layers.fused_moe.moe_align_block_size import (
moe_align_block_size_triton,
moe_align_block_size,
)
from vllm.triton_utils import triton
@@ -21,60 +20,6 @@ def get_topk_ids(num_tokens: int, num_experts: int, topk: int) -> torch.Tensor:
)
def check_correctness(num_tokens, num_experts=256, block_size=256, topk=8):
"""
Verifies vllm vs. Triton
"""
topk_ids = get_topk_ids(num_tokens, num_experts, topk)
# 1. malloc space for triton and vllm
# malloc enough space (max_num_tokens_padded) for the sorted ids
max_num_tokens_padded = topk_ids.numel() + num_experts * (block_size - 1)
sorted_ids_triton = torch.empty(
(max_num_tokens_padded,), dtype=torch.int32, device="cuda"
)
expert_ids_triton = torch.empty(
(max_num_tokens_padded // block_size,), dtype=torch.int32, device="cuda"
)
num_tokens_post_pad_triton = torch.empty((1,), dtype=torch.int32, device="cuda")
sorted_ids_vllm = torch.empty_like(sorted_ids_triton)
expert_ids_vllm = torch.empty_like(expert_ids_triton)
num_tokens_post_pad_vllm = torch.empty_like(num_tokens_post_pad_triton)
# 2. run implementations
moe_align_block_size_triton(
topk_ids,
num_experts,
block_size,
sorted_ids_triton,
expert_ids_triton,
num_tokens_post_pad_triton,
)
ops.moe_align_block_size(
topk_ids,
num_experts,
block_size,
sorted_ids_vllm,
expert_ids_vllm,
num_tokens_post_pad_vllm,
)
print(f"✅ VLLM implementation works with {num_experts} experts!")
# 3. compare results
if torch.allclose(expert_ids_triton, expert_ids_vllm) and torch.allclose(
num_tokens_post_pad_triton, num_tokens_post_pad_vllm
):
print("✅ Triton and VLLM implementations match.")
else:
print("❌ Triton and VLLM implementations DO NOT match.")
print("Triton expert_ids:", expert_ids_triton)
print("VLLM expert_ids:", expert_ids_vllm)
print("Triton num_tokens_post_pad:", num_tokens_post_pad_triton)
print("VLLM num_tokens_post_pad:", num_tokens_post_pad_vllm)
# test configurations
num_tokens_range = [1, 16, 256, 4096]
num_experts_range = [16, 64, 224, 256, 280, 512]
@@ -87,8 +32,8 @@ configs = list(itertools.product(num_tokens_range, num_experts_range, topk_range
x_names=["num_tokens", "num_experts", "topk"],
x_vals=configs,
line_arg="provider",
line_vals=["vllm", "triton"], # "triton"
line_names=["VLLM", "Triton"], # "Triton"
line_vals=["vllm"],
line_names=["vLLM"],
plot_name="moe-align-block-size-performance",
args={},
)
@@ -98,36 +43,11 @@ def benchmark(num_tokens, num_experts, topk, provider):
block_size = 256
topk_ids = get_topk_ids(num_tokens, num_experts, topk)
max_num_tokens_padded = topk_ids.numel() + num_experts * (block_size - 1)
sorted_ids = torch.empty((max_num_tokens_padded,), dtype=torch.int32, device="cuda")
max_num_m_blocks = max_num_tokens_padded // block_size
expert_ids = torch.empty((max_num_m_blocks,), dtype=torch.int32, device="cuda")
num_tokens_post_pad = torch.empty((1,), dtype=torch.int32, device="cuda")
quantiles = [0.5, 0.2, 0.8]
if provider == "vllm":
ms, min_ms, max_ms = triton.testing.do_bench(
lambda: ops.moe_align_block_size(
topk_ids,
num_experts,
block_size,
sorted_ids.clone(),
expert_ids.clone(),
num_tokens_post_pad.clone(),
),
quantiles=quantiles,
)
elif provider == "triton":
ms, min_ms, max_ms = triton.testing.do_bench(
lambda: moe_align_block_size_triton(
topk_ids,
num_experts,
block_size,
sorted_ids.clone(),
expert_ids.clone(),
num_tokens_post_pad.clone(),
),
lambda: moe_align_block_size(topk_ids, block_size, num_experts),
quantiles=quantiles,
)
@@ -151,6 +71,4 @@ if __name__ == "__main__":
)
args = parser.parse_args()
print("Running correctness check...")
check_correctness(num_tokens=1024, num_experts=args.num_experts, topk=args.topk)
benchmark.run(print_data=True, show_plots=True)