mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
[FDConfig]Remove max_model_len in FDConfig (#4350)
* modify max_model_len * fix unittest * fix unittest --------- Co-authored-by: root <root@yqlcc01-sys-rpm12rzmwjd.yqlcc01.baidu.com>
This commit is contained in:
@@ -630,7 +630,7 @@ class EngineService:
|
||||
available_blocks=available_blocks,
|
||||
block_size=self.cfg.cache_config.block_size,
|
||||
reserved_output_blocks=self.cfg.cache_config.enc_dec_block_num,
|
||||
max_num_batched_tokens=self.cfg.max_model_len,
|
||||
max_num_batched_tokens=self.cfg.model_config.max_model_len,
|
||||
batch=num_prefill_batch,
|
||||
)
|
||||
if self.cfg.scheduler_config.splitwise_role != "mixed":
|
||||
|
||||
Reference in New Issue
Block a user