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

[Frontend] Use new Renderer for Completions and Tokenize API (#32863)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-01-31 20:51:15 +08:00
committed by GitHub
parent 8980001c93
commit f0a1c8453a
64 changed files with 2116 additions and 2003 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/models/language/pooling/test_truncation_control.py
View File

@@ -29,7 +29,8 @@ def test_smaller_truncation_size(
model_name, runner="pooling", max_model_len=max_model_len
) as vllm_model:
vllm_output = vllm_model.llm.embed(
input_str, truncate_prompt_tokens=truncate_prompt_tokens
input_str,
tokenization_kwargs=dict(truncate_prompt_tokens=truncate_prompt_tokens),
)
prompt_tokens = vllm_output[0].prompt_token_ids
@@ -44,7 +45,8 @@ def test_max_truncation_size(vllm_runner, model_name=MODEL_NAME, input_str=input
model_name, runner="pooling", max_model_len=max_model_len
) as vllm_model:
vllm_output = vllm_model.llm.embed(
input_str, truncate_prompt_tokens=truncate_prompt_tokens
input_str,
tokenization_kwargs=dict(truncate_prompt_tokens=truncate_prompt_tokens),
)
prompt_tokens = vllm_output[0].prompt_token_ids
@@ -64,7 +66,8 @@ def test_bigger_truncation_size(
) as vllm_model,
):
llm_output = vllm_model.llm.embed(
input_str, truncate_prompt_tokens=truncate_prompt_tokens
input_str,
tokenization_kwargs=dict(truncate_prompt_tokens=truncate_prompt_tokens),
)
assert (