apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Executor]CUDAGraph support Speculate Decode (#3769)
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
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* success run ngram

* Revert "[Code Simplification] remove cum_offsets (#3410)"

This reverts commit 32b39620bc.

* success run ngram5 tp4 42bs

* success run ngram5 tp4 42bs

* mtp draft commit

* add decorator for target model

* enable draft model in cudagraph v0.5

* revert revrt cum_offset

* enable target model in cudagraph v0.9 And clean debug code

* Revert "success run ngram"

This reverts commit 8351e83993.

* add reverted code

* enable target model in cudagraph v0.9

* solve comment

* fix bid < 0

* Enable Target Model Padding And Draft Model in cudagraph

* solve problem

* delete rebuild padding debug note

* fast compile

* Add capture list for mtp

* success run 256 tp1 mtp

* Enable Lite TP2 Bsz256

* realy enable tp2 bsz 256

* fix problem

* Solve problem for Draft model in cudagraph

* Solve comment

* replace emptytensor as zeros

* Solve comments

* Revert "fast compile"

This reverts commit 834639a7ff.

* fix bug

* fix merge bug

* fix typo

* fix bug

---------

Co-authored-by: lizexu <2694294196@qq.com>
Co-authored-by: littledgg <1658565283@qq.com>
Co-authored-by: zeroRains <linjunlu@zerorains.top>
Co-authored-by: gongshaotian <gstain5555@outlook.com>
This commit is contained in:
RAM
2025-10-09 21:18:29 +08:00
committed by GitHub
parent 7b1689f437
commit aa27b03bc0
19 changed files with 250 additions and 139 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
fastdeploy/spec_decode/base.py
View File

@@ -33,24 +33,25 @@ class Proposer(ABC):
the speculative decoding framework
"""
def __init__(self, cfg: FDConfig):
def __init__(self, fd_config: FDConfig):
"""
Init Speculative proposer
"""
cfg.parallel_config.tp_group = None
self.cfg = deepcopy(cfg)
cfg.parallel_config.tp_group = dist.get_group(
cfg.parallel_config.data_parallel_rank + envs.FD_TP_GROUP_GID_OFFSET
fd_config.parallel_config.tp_group = None
self.fd_config = deepcopy(fd_config)
fd_config.parallel_config.tp_group = dist.get_group(
fd_config.parallel_config.data_parallel_rank + envs.FD_TP_GROUP_GID_OFFSET
)
self.cfg.parallel_config.tp_group = dist.get_group(
cfg.parallel_config.data_parallel_rank + envs.FD_TP_GROUP_GID_OFFSET
self.fd_config.parallel_config.tp_group = dist.get_group(
fd_config.parallel_config.data_parallel_rank + envs.FD_TP_GROUP_GID_OFFSET
)
self.parallel_config = self.cfg.parallel_config
self.model_config = self.cfg.model_config
self.speculative_config = self.cfg.speculative_config
self.cache_config = self.cfg.cache_config
self.quant_config = self.cfg.quant_config
self.scheduler_config = self.cfg.scheduler_config
self.parallel_config = self.fd_config.parallel_config
self.model_config = self.fd_config.model_config
self.speculative_config = self.fd_config.speculative_config
self.cache_config = self.fd_config.cache_config
self.quant_config = self.fd_config.quant_config
self.graph_opt_config = self.fd_config.graph_opt_config
self.scheduler_config = self.fd_config.scheduler_config
self.max_num_seqs = self.scheduler_config.max_num_seqs
self.max_model_len = self.parallel_config.max_model_len