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

Enable V1 for Hybrid SSM/Attention Models (#20016)

Browse Source 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Stanislaw Wozniak <stw@zurich.ibm.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
This commit is contained in:
Thomas Parnell
2025-07-04 19:46:53 +02:00
committed by GitHub
parent ffe00ef77a
commit 2f35a022e6
14 changed files with 399 additions and 134 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/v1/test_oracle.py
View File

@@ -13,7 +13,6 @@ UNSUPPORTED_MODELS_V1 = [
"openai/whisper-large-v3", # transcription
"facebook/bart-large-cnn", # encoder decoder
"state-spaces/mamba-130m-hf", # mamba1
"hmellor/tiny-random-BambaForCausalLM", # hybrid
"BAAI/bge-m3", # embedding
]