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

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

View File

@@ -26,7 +26,7 @@ def test_smaller_truncation_size(vllm_runner,
truncate_prompt_tokens = 10
with vllm_runner(model_name, task="embed",
with vllm_runner(model_name, runner="pooling",
max_model_len=max_model_len) as vllm_model:
vllm_output = vllm_model.llm.encode(
input_str, truncate_prompt_tokens=truncate_prompt_tokens)
@@ -41,7 +41,7 @@ def test_max_truncation_size(vllm_runner,
input_str=input_str):
truncate_prompt_tokens = -1
with vllm_runner(model_name, task="embed",
with vllm_runner(model_name, runner="pooling",
max_model_len=max_model_len) as vllm_model:
vllm_output = vllm_model.llm.encode(
input_str, truncate_prompt_tokens=truncate_prompt_tokens)
@@ -58,7 +58,7 @@ def test_bigger_truncation_size(vllm_runner,
truncate_prompt_tokens = max_model_len + 1
with pytest.raises(ValueError), vllm_runner(
model_name, task="embed",
model_name, runner="pooling",
max_model_len=max_model_len) as vllm_model:
llm_output = vllm_model.llm.encode(