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

[Feature] Unify the registration name recognition for tool_parser and reasoning_parser to “-” (#4668)

Browse Source 
* parser register name unify

* change ernie_x1 to ernie-x1

* change ernie4_5_vl to ernie-45-vl

* fix unit test
This commit is contained in:
kxz2002
2025-10-31 10:45:27 +08:00
committed by GitHub
parent 82bd7e5db4
commit a2870ed4a9
16 changed files with 28 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
benchmarks/yaml/x1-64k-w4a8c8-tp4.yaml
View File

@@ -1,5 +1,5 @@
reasoning-parser: ernie_x1
tool_call_parser: ernie_x1
reasoning-parser: ernie-x1
tool_call_parser: ernie-x1
tensor_parallel_size: 4
max_model_len: 65536
max_num_seqs: 128

4
benchmarks/yaml/x1-a3b-128k-wint8-h800-tp1.yaml
View File

@@ -1,7 +1,7 @@
tensor_parallel_size: 1
max_model_len: 131072
max_num_seqs: 32
reasoning_parser: ernie_x1
tool_call_parser: ernie_x1
reasoning_parser: ernie-x1
tool_call_parser: ernie-x1
load_choices: "default_v1"
quantization: wint8