Skip to content

[Optimization] Support logprob async copy #6362

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Sunny-bot1 wants to merge 5 commits into
base: develop
Choose a base branch
from
+18 −8
Open

[Optimization] Support logprob async copy #6362

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a8e07aa
support logprob async copy
Sunny-bot1 Feb 5, 2026
4b18047
fix prompt logprob
Sunny-bot1 Feb 5, 2026
3ac5902
Merge branch 'logprob_async' of https://github.com/Sunny-bot1/FastDep…
Sunny-bot1 Feb 5, 2026
3fdd70b
Merge branch 'develop' of https://github.com/PaddlePaddle/FastDeploy …
Sunny-bot1 Feb 5, 2026
a8aa492
fix xpu
Sunny-bot1 Feb 7, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 12 additions & 4 deletions fastdeploy/model_executor/layers/sample/sampler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -478,10 +478,18 @@ def gather_logprobs(
else:
indices = token_ids
top_logprobs = token_logprobs
indices = indices.cpu()
top_logprobs = top_logprobs.cpu()
token_ranks = token_ranks.cpu()
return LogprobsTensors(indices, top_logprobs, token_ranks)
if current_platform.is_cuda():
indices_cpu = paddle.empty_like(indices, device="cpu").pin_memory()
top_logprobs_cpu = paddle.empty_like(top_logprobs, device="cpu").pin_memory()
token_ranks_cpu = paddle.empty_like(token_ranks, device="cpu").pin_memory()
indices_cpu.copy_(indices, False)
top_logprobs_cpu.copy_(top_logprobs, False)
token_ranks_cpu.copy_(token_ranks, False)
else:
indices_cpu = indices.cpu()
top_logprobs_cpu = top_logprobs.cpu()
token_ranks_cpu = token_ranks.cpu()
return LogprobsTensors(indices_cpu, top_logprobs_cpu, token_ranks_cpu)

def forward_cuda(
self,
Expand Down
2 changes: 1 addition & 1 deletion fastdeploy/model_executor/pre_and_post_process.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -464,7 +464,7 @@ def save_output_normal(
sampler_output, model_output.index_to_batch_id, model_output.enable_pd_reorder
)
save_output_topk(
sampler_output.sampled_token_ids,
share_inputs["sampled_token_ids"],
sampler_output.logprobs_tensors.logprob_token_ids,
sampler_output.logprobs_tensors.logprobs,
sampler_output.logprobs_tensors.selected_token_ranks,
Expand Down
2 changes: 2 additions & 0 deletions fastdeploy/worker/gpu_model_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3119,6 +3119,8 @@ def _get_prompt_logprobs_list(
token_ids, logprobs, ranks = self.sampler.gather_logprobs(
raw_logprobs, num_prompt_logprobs, prompt_token_ids_tensor
)
# Synchronize before using token_ids, logprobs and ranks to ensure async copy are completed.
paddle.device.synchronize()
chunk_slice = slice(start_idx, start_idx + num_logits)
logprobs_tensors.logprob_token_ids[chunk_slice].copy_(token_ids, False)
logprobs_tensors.logprobs[chunk_slice].copy_(logprobs, False)
Expand Down
6 changes: 3 additions & 3 deletions fastdeploy/worker/output.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,9 +119,9 @@ def slice_rows(self, start: int, end: int):
"""
with paddle.no_grad():
return LogprobsTensors(
paddle.to_tensor(self.logprob_token_ids[start:end], place=self.logprob_token_ids.place),
paddle.to_tensor(self.logprobs[start:end], place=self.logprob_token_ids.place),
paddle.to_tensor(self.selected_token_ranks[start:end], place=self.logprob_token_ids.place),
paddle.to_tensor(self.logprob_token_ids.cpu()[start:end], place="cpu"),
paddle.to_tensor(self.logprobs.cpu()[start:end], place="cpu"),
paddle.to_tensor(self.selected_token_ranks.cpu()[start:end], place="cpu"),
)


Expand Down
Loading