* 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:
Zhang Yulong
2025-08-21 16:49:20 +08:00
committed by GitHub
parent c83381d650
commit b7eee3aec1
13 changed files with 150 additions and 392 deletions
+8
View File
@@ -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/