Skip to content

GitLab

Unverified Commit 6128f7cf authored by Yineng Zhang's avatar Yineng Zhang Committed by GitHub
Browse files

fix: specify dtype with begin_forward aka plan (#2404)

parent a2486eb5
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
python/sglang/srt/layers/attention/flashinfer_backend.py
View file @ 6128f7cf
...@@ -678,6 +678,7 @@ class FlashInferIndicesUpdaterPrefill: ...@@ -678,6 +678,7 @@ class FlashInferIndicesUpdaterPrefill:
self.num_qo_heads, self.num_qo_heads,
self.num_kv_heads, self.num_kv_heads,
self.head_dim, self.head_dim,
q_data_type=self.q_data_type,
) )
# cached part # cached part
...@@ -691,6 +692,7 @@ class FlashInferIndicesUpdaterPrefill: ...@@ -691,6 +692,7 @@ class FlashInferIndicesUpdaterPrefill:
self.num_kv_heads, self.num_kv_heads,
self.head_dim, self.head_dim,
1, 1,
q_data_type=self.q_data_type,
) )
......
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