Skip to content

GitLab

"tests/models/decoder_only/language/test_models.py" did not exist on "de60a3fb93957dce6b242299b5d163f02ef7f383"
Commit d2c20c55 authored by 王敏's avatar 王敏
Browse files

[fix]解决dp+graph+naive all2all dispatch时的维度不匹配问题

parent 3cd3d1e6
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
vllm/v1/worker/gpu_model_runner.py
View file @ d2c20c55
...@@ -3026,6 +3026,8 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin): ...@@ -3026,6 +3026,8 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
num_tokens_across_dp = num_tokens_after_padding num_tokens_across_dp = num_tokens_after_padding
num_tokens_after_padding = int(num_tokens_after_padding[0].item()) num_tokens_after_padding = int(num_tokens_after_padding[0].item())
num_tokens = num_tokens_after_padding
attn_metadata: Optional[PerLayerAttnMetadata] = None attn_metadata: Optional[PerLayerAttnMetadata] = None
# If force_attention is True, we always capture attention. Otherwise, # If force_attention is True, we always capture attention. Otherwise,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment