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

[V0 Deprecation] Remove pooling model support in V0 (#23434)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Maximilien de Bayser
2025-08-29 04:04:02 -03:00
committed by GitHub
parent 934bebf192
commit 2554b27baa
38 changed files with 99 additions and 808 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
tests/entrypoints/offline_mode/test_offline_mode.py
View File

@@ -32,15 +32,16 @@ MODEL_CONFIGS = [
"tensor_parallel_size": 1,
"tokenizer_mode": "mistral",
},
{
"model": "sentence-transformers/all-MiniLM-L12-v2",
"enforce_eager": True,
"gpu_memory_utilization": 0.20,
"max_model_len": 64,
"max_num_batched_tokens": 64,
"max_num_seqs": 64,
"tensor_parallel_size": 1,
},
# TODO: re-enable once these tests are run with V1
# {
# "model": "sentence-transformers/all-MiniLM-L12-v2",
# "enforce_eager": True,
# "gpu_memory_utilization": 0.20,
# "max_model_len": 64,
# "max_num_batched_tokens": 64,
# "max_num_seqs": 64,
# "tensor_parallel_size": 1,
# },
]