EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Revert "fix some typos" (#6244)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-05-12 12:53:26 -07:00
committed by GitHub
parent bad7c26fdc
commit e8e18dcdcc
95 changed files with 276 additions and 276 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
sgl-kernel/benchmark/bench_moe_align_block_size.py
View File

@@ -177,7 +177,7 @@ def calculate_diff(num_tokens, num_experts=256, block_size=128, topk=8):
expert_ids_vllm = torch.zeros_like(expert_ids_cuda)
num_tokens_post_pad_vllm = torch.empty_like(num_tokens_post_pad_cuda)
# compare the performance of CUDA, triton and vllm implementation
# compare the performance of cuda, triton and vllm implementation
sgl_moe_align_block_size(
topk_ids,
num_experts,
@@ -349,7 +349,7 @@ def benchmark(num_tokens, num_experts, topk, provider):
),
quantiles=quantiles,
)
else: # vLLM
else: # vllm
try:
ms, min_ms, max_ms = triton.testing.do_bench(
lambda: ops.moe_align_block_size(