biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V1] [Hybrid] Mamba1 Automatic Prefix Caching (#26377)

Browse Source 
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
This commit is contained in:
Asaf Joseph Gardin
2025-11-02 14:16:23 +02:00
committed by GitHub
parent 73444b7b56
commit 00b31a36a2
16 changed files with 442 additions and 153 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/config.py
View File

@@ -299,7 +299,7 @@ class MambaModelConfig(VerifyAndUpdateConfig):
if model_config.supports_mamba_prefix_caching:
logger.info(
"Warning: Prefix caching is currently enabled. "
"Its support for Mamba2 layers is experimental. "
"Its support for Mamba layers is experimental. "
"Please report any issues you may observe."
)
else: