mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
* 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
9 lines
200 B
YAML
9 lines
200 B
YAML
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/
|