Skip to content

GitLab

Unverified Commit 3c3d6255 authored by Hank Han's avatar Hank Han Committed by GitHub
Browse files

[fix]missing prefix_lens_cpu init when p/d disaggregation (#11196)

parent 546914fa
Hide whitespace changes
Inline Side-by-side
Showing with 8 additions and 0 deletions
python/sglang/srt/disaggregation/decode.py
View file @ 3c3d6255
...@@ -523,11 +523,19 @@ class DecodePreallocQueue: ...@@ -523,11 +523,19 @@ class DecodePreallocQueue:
dtype=torch.int64, dtype=torch.int64,
device=self.token_to_kv_pool_allocator.device, device=self.token_to_kv_pool_allocator.device,
), ),
prefix_lens_cpu=torch.tensor(
[0],
dtype=torch.int64,
),
seq_lens=torch.tensor( seq_lens=torch.tensor(
[num_tokens], [num_tokens],
dtype=torch.int64, dtype=torch.int64,
device=self.token_to_kv_pool_allocator.device, device=self.token_to_kv_pool_allocator.device,
), ),
seq_lens_cpu=torch.tensor(
[num_tokens],
dtype=torch.int64,
),
last_loc=torch.tensor( last_loc=torch.tensor(
[-1], [-1],
dtype=torch.int64, dtype=torch.int64,
......
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