Files
FastDeploy/tests/ce/deploy/21b_mtp.yaml
Zhang Yulong b7eee3aec1 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
2025-08-21 16:49:20 +08:00

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/