apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 08:16:42 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[FDConfig]Remove splitwise_role and engine_worker_queue_port in FDConfig (#4147)
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 
* remove splitwise_role and engine_worker_queue_port

* fix xpu

* fix xpu

* fix xpu

* fix unittest

* resolve conflct
This commit is contained in:
YuanRisheng
2025-09-19 17:01:52 +08:00
committed by GitHub
parent ee9d8a840a
commit 24180fba0a
23 changed files with 129 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/spec_decode/mtp.py
View File

@@ -150,7 +150,7 @@ class MTPProposer(Proposer):
max_num_blocks=self.num_gpu_blocks, kv_cache_quant_type=kv_cache_quant_type
)
if not self.parallel_config.do_profile and (
self.cache_config.enable_prefix_caching or self.parallel_config.splitwise_role != "mixed"
self.cache_config.enable_prefix_caching or self.scheduler_config.splitwise_role != "mixed"
):
cache_kvs_list = []
for i in range(
@@ -267,7 +267,7 @@ class MTPProposer(Proposer):
self.main_model_num_gpu_blocks = num_gpu_blocks
self.num_gpu_blocks = int(num_gpu_blocks * self.speculative_config.num_gpu_block_expand_ratio)
if not (self.cache_config.enable_prefix_caching or self.parallel_config.splitwise_role != "mixed"):
if not (self.cache_config.enable_prefix_caching or self.scheduler_config.splitwise_role != "mixed"):
self.initialize_kv_cache()
# Reset free list