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

[BugFix]fix iluvatar_model_runner about dsa_cache (#6733)

Browse Source 
* fix iluvatar_model_runner
This commit is contained in:
AIbin
2026-03-10 16:10:35 +08:00
committed by GitHub
parent c3aceb6bdc
commit 54581b8653
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/worker/iluvatar_model_runner.py
+2
View File
@@ -59,6 +59,8 @@ class IluvatarModelRunner(GPUModelRunner):
assert not self.cache_config.enable_prefix_caching, "Iluvatar does not support prefix caching"
self.mla_cache = envs.FD_ATTENTION_BACKEND == "MLA_ATTN"
assert not self.mla_cache, "Iluvatar does not support MLA"
self.dsa_cache = envs.FD_ATTENTION_BACKEND == "DSA_ATTN"
assert not self.dsa_cache, "Iluvatar does not support DSA_ATTN"
if self.enable_mm:
assert (
not self.cache_config.enable_chunked_prefill