chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages 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

8
python/sglang/srt/models/mllama.py
View File

@@ -537,8 +537,8 @@ class MllamaTextCrossAttention(nn.Module):
quant_config=quant_config,
prefix=add_prefix("o_proj", prefix),
)
# vllm.model_executor.layers.layernorm.RMSNorm has a precision issue,
# use HuggingFace's instead
# vllm.model_executor.layers.layernorm.RMSNorm has precision issue,
# use huggingface's instead
self.q_norm = MllamaTextRMSNorm(self.head_dim, eps=config.rms_norm_eps)
self.k_norm = MllamaTextRMSNorm(self.head_dim, eps=config.rms_norm_eps)
self.scaling = self.head_dim**-0.5
@@ -979,8 +979,8 @@ class MllamaForConditionalGeneration(nn.Module):
cross_attention_states = None
if self.capture_mode:
# NOTE: when doing CUDA graph capture, we do not want to skip cross attention
# Make is a constant value to avoid CUDA graph capture issue
# NOTE: when doing cuda graph capture, we do not want to skip cross attention
# Make is a constant value to avoid cuda graph capture issue
skip_cross_attention = False
else:
# NOTE: we do not need image_inputs when prefill