apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-30 11:26:39 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

[Executor]CUDAGraph support Speculate Decode (#4258)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details

Browse Source 
* [Executor]CUDAGraph support Speculate Decode

* fix problem

* solve problem

* fix

* fast compile

* CUDAGraph + mtp support eb5(only target model)

* Revert "fast compile"

This reverts commit 3cfe8373ed.

* fix precommit

* solve comment

* fix comment about #pragram unroll

---------

Co-authored-by: gongshaotian <gstain5555@outlook.com>
Co-authored-by: gongshaotian <gstian5555@outlook.com>
This commit is contained in:
Jundong Liu
2025-10-13 15:21:41 +08:00
committed by GitHub
parent 07db281647
commit 0b7a5778ab
16 changed files with 265 additions and 134 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/model_executor/layers/sample/sampler.py
View File

@@ -395,6 +395,7 @@ class SpeculativeSampler(nn.Layer):
sampling_metadata: SamplingMetadata,
max_model_len: int,
share_inputs: List[paddle.Tensor],
accept_all_drafts: bool = False,
) -> paddle.Tensor:
""" """
@@ -451,6 +452,7 @@ class SpeculativeSampler(nn.Layer):
self.speculative_verify_window,
True, # enable_topp
self.speculative_benchmark_mode,
accept_all_drafts,
)
return None