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

[V1] [Hybrid] Mamba2 Automatic Prefix Caching (#25752)

Browse Source 
Signed-off-by: Stanislaw Wozniak <stw@zurich.ibm.com>
Signed-off-by: Thomas Ortner <boh@zurich.ibm.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Thomas Ortner <boh@zurich.ibm.com>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
This commit is contained in:
Stan Wozniak
2025-10-04 06:34:22 +02:00
committed by GitHub
parent 9705fba7b7
commit ea507c3a93
18 changed files with 917 additions and 147 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/models/mamba2.py
View File

@@ -222,11 +222,8 @@ class Mamba2ForCausalLM(nn.Module, HasInnerState, IsAttentionFree):
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
config = vllm_config.model_config.hf_config
cache_config = vllm_config.cache_config
lora_config = vllm_config.lora_config
scheduler_config = vllm_config.scheduler_config
assert not cache_config.enable_prefix_caching, \
"Mamba does not support prefix caching"
super().__init__()
self.config = config