mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
Update CI (#3474)
* update CI cases * update CI cases * update CI cases * update CI cases * Merge upstream/develop and resolve directory rename conflict * Merge upstream/develop and resolve directory rename conflict * Merge upstream/develop and resolve directory rename conflict * update deploy * update deploy * update deploy * update deploy * update deploy
This commit is contained in:
@@ -0,0 +1,8 @@
|
||||
max_model_len: 32768
|
||||
max_num_seqs: 128
|
||||
tensor_parallel_size: 1
|
||||
quantization: wint4
|
||||
speculative_config:
|
||||
method: mtp
|
||||
num_speculative_tokens: 1
|
||||
model: /MODELDATA/ernie-4_5-21b-a3b-bf16-paddle/mtp/
|
||||
Reference in New Issue
Block a user