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

[Model] Add LFM2 architecture (#22845)

Browse Source 
Signed-off-by: Paul Pak <paulpak58@gmail.com>
This commit is contained in:
Paul Pak
2025-08-21 01:35:07 -06:00
committed by GitHub
parent 31282401b6
commit 2e2000f352
11 changed files with 960 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/config/compilation.py
View File

@@ -337,6 +337,7 @@ class CompilationConfig:
"vllm.unified_attention_with_output",
"vllm.mamba_mixer2",
"vllm.mamba_mixer",
"vllm.short_conv",
]
def compute_hash(self) -> str: