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

[Deprecation][2/N] Replace --task with --runner and --convert (#21470)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Cyrus Leung
2025-07-28 10:42:40 +08:00
committed by GitHub
parent 8f605ee309
commit 86ae693f20
94 changed files with 1117 additions and 1083 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
tests/models/language/pooling/test_scoring.py
View File

@@ -37,7 +37,9 @@ def test_cross_encoder_1_to_1(vllm_runner, hf_runner, model_name):
with hf_runner(model_name, dtype=DTYPE, is_cross_encoder=True) as hf_model:
hf_outputs = hf_model.predict([text_pair]).tolist()
with vllm_runner(model_name, task="score", dtype=DTYPE,
with vllm_runner(model_name,
runner="pooling",
dtype=DTYPE,
max_model_len=None) as vllm_model:
vllm_outputs = vllm_model.score(text_pair[0], text_pair[1])
@@ -56,7 +58,9 @@ def test_cross_encoder_1_to_N(vllm_runner, hf_runner, model_name):
with hf_runner(model_name, dtype=DTYPE, is_cross_encoder=True) as hf_model:
hf_outputs = hf_model.predict(text_pairs).tolist()
with vllm_runner(model_name, task="score", dtype=DTYPE,
with vllm_runner(model_name,
runner="pooling",
dtype=DTYPE,
max_model_len=None) as vllm_model:
vllm_outputs = vllm_model.score(TEXTS_1[0], TEXTS_2)
@@ -76,7 +80,9 @@ def test_cross_encoder_N_to_N(vllm_runner, hf_runner, model_name):
with hf_runner(model_name, dtype=DTYPE, is_cross_encoder=True) as hf_model:
hf_outputs = hf_model.predict(text_pairs).tolist()
with vllm_runner(model_name, task="score", dtype=DTYPE,
with vllm_runner(model_name,
runner="pooling",
dtype=DTYPE,
max_model_len=None) as vllm_model:
vllm_outputs = vllm_model.score(TEXTS_1, TEXTS_2)
@@ -103,7 +109,7 @@ def test_embedding_1_to_1(vllm_runner, hf_runner, emb_model_name):
]
with vllm_runner(emb_model_name,
task="embed",
runner="pooling",
dtype=DTYPE,
max_model_len=None) as vllm_model:
vllm_outputs = vllm_model.score(text_pair[0], text_pair[1])
@@ -131,7 +137,7 @@ def test_embedding_1_to_N(vllm_runner, hf_runner, emb_model_name):
]
with vllm_runner(emb_model_name,
task="embed",
runner="pooling",
dtype=DTYPE,
max_model_len=None) as vllm_model:
vllm_outputs = vllm_model.score(TEXTS_1[0], TEXTS_2)
@@ -160,7 +166,7 @@ def test_embedding_N_to_N(vllm_runner, hf_runner, emb_model_name):
]
with vllm_runner(emb_model_name,
task="embed",
runner="pooling",
dtype=DTYPE,
max_model_len=None) as vllm_model:
vllm_outputs = vllm_model.score(TEXTS_1, TEXTS_2)