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

Add typo checker in pre-commit (#6179)

Browse Source 
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
This commit is contained in:
applesaucethebun
2025-05-11 00:55:00 -04:00
committed by GitHub
parent de167cf5fa
commit 2ce8793519
99 changed files with 154 additions and 144 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
sgl-kernel/python/sgl_kernel/elementwise.py
View File

@@ -229,7 +229,7 @@ def apply_rope_with_cos_sin_cache_inplace(
Whether to use Neox style RoPE, default: ``True``.
* If ``True``, the last dimension of the query/key tensor is not interleaved, i.e.,
we rorate the first half dimensions ``([..., :head_dim//2])`` and the second half
we rotate the first half dimensions ``([..., :head_dim//2])`` and the second half
dimensions ``([..., head_dim//2:])``.
* If ``False``, the last dimension of the query/key tensor is interleaved, i.e.,

2
sgl-kernel/python/sgl_kernel/flash_attn.py
View File

@@ -17,7 +17,7 @@ def is_fa3_supported(device=None) -> bool:
# Between sm80/sm87 and sm86/sm89 is the shared memory size. you can follow the link below for more information
# https://docs.nvidia.com/cuda/cuda-c-programming-guide/#shared-memory-8-x
# And for sgl-kernel right now, we can build fa3 on sm80/sm86/sm89/sm90a.
# Thats mean if you use A100/A*0/L20/L40/L40s/4090 you can use fa3.
# That means if you use A100/A*0/L20/L40/L40s/4090 you can use fa3.
return (
torch.cuda.get_device_capability(device)[0] == 9
or torch.cuda.get_device_capability(device)[0] == 8

6
sgl-kernel/python/sgl_kernel/moe.py
View File

@@ -45,10 +45,10 @@ def moe_fused_gate(
):
# This fused kernel function is used to select topk expert in a hierarchical 2-layer fashion
# it split group of expert into num_expert_group, and use top2 expert weight sum in each group
# as the group weight to select exerpt groups and then select topk experts within the selected groups
# as the group weight to select expert groups and then select topk experts within the selected groups
# the #experts is decided by the input tensor shape and we currently only support power of 2 #experts
# and #experts should be divisible by num_expert_group. #expert/num_expert_group <= 32 is limitted for now.
# for non-supported case, we suggestion to use the biased_grouped_topk func in sglang.srt.layers.moe.topk
# and #experts should be divisible by num_expert_group. #expert/num_expert_group <= 32 is limited for now.
# for non-supported case, we suggest to use the biased_grouped_topk func in sglang.srt.layers.moe.topk
# n_share_experts_fusion: if > 0, the last expert will be replaced with a round-robin shared expert
# routed_scaling_factor: if > 0, the last expert will be scaled by this factor
return torch.ops.sgl_kernel.moe_fused_gate.default(