mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
[BugFix] fix mtp logprob bugs in chunk prefill (#5234)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
* fix mtp logprob bugs in chunk prefill * merge code * fix Request CONFLICT * Revert "fix Request CONFLICT" This reverts commit7a438e4119. * Revert "merge code" This reverts commit3839559b83. * fix * remove print * fix --------- Co-authored-by: sunlei1024 <sunlei5788@gmail.com>
This commit is contained in:
@@ -349,8 +349,11 @@ def post_process_specualate(
|
||||
sampler_output.token_num_per_batch,
|
||||
sampler_output.cu_batch_token_offset,
|
||||
model_output.not_need_stop,
|
||||
model_output.seq_lens_decoder,
|
||||
model_output.prompt_lens,
|
||||
3, # mtype
|
||||
model_output.mp_rank,
|
||||
save_each_rank,
|
||||
)
|
||||
|
||||
# Update pre_ids through accept tokens
|
||||
|
||||
Reference in New Issue
Block a user