apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-09-27 04:46:16 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

fix mtp bug in pd-split mode (#2970)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source
This commit is contained in:
freeliuzc
2025-07-23 15:31:16 +08:00
committed by GitHub
parent 6c4cfd9359
commit a39a67334c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/spec_decode/mtp.py
View File

@@ -340,7 +340,7 @@ class MTPProposer(Proposer):
self.model_inputs["pre_ids"][idx : idx + 1] = request.prompt_token_ids[-1]
prefill_token_num = self.max_draft_token_num + 1
self.model_inputs["draft_tokens"][idx : idx + 1, 0:1] = paddle.to_tensor(
request.draft_token_ids[0:1], dtype="int64"
request.draft_token_ids[1:2], dtype="int64"
)
self.model_inputs["seq_lens_encoder"][idx : idx + 1] = 0