apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

fix fetch request bug (#5712)

Browse Source
This commit is contained in:
kevin
2025-12-24 15:20:56 +08:00
committed by GitHub
parent 4e392e8337
commit 89675203d3
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/config.py
+4 -1
View File
@@ -1518,7 +1518,10 @@ class FDConfig:
self.long_prefill_token_threshold = int(self.model_config.max_model_len * 0.04)
self.cache_config.postprocess(self.scheduler_config.max_num_batched_tokens, self.scheduler_config.max_num_seqs)
self.cache_config.max_block_num_per_seq = int(self.model_config.max_model_len // self.cache_config.block_size)
self.cache_config.max_block_num_per_seq = int(
(self.model_config.max_model_len + self.cache_config.block_size - 1) // self.cache_config.block_size
+ self.cache_config.enc_dec_block_num
)
if self.model_config is not None and self.model_config.enable_mm and not envs.ENABLE_V1_KVCACHE_SCHEDULER:
self.cache_config.enable_prefix_caching = False