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

[beam search] add output for manually checking the correctness (#8684)

Browse Source
This commit is contained in:
youkaichao 2024-09-20 19:55:33 -07:00 committed by GitHub
parent 0455c46ed4
commit 0faab90eb0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
tests/samplers/test_beam_search.py
View File

@ -11,7 +11,7 @@ import pytest
# 3. Use the model "huggyllama/llama-7b".
MAX_TOKENS = [128]
BEAM_WIDTHS = [4]
MODELS = ["facebook/opt-125m"]
MODELS = ["TinyLlama/TinyLlama-1.1B-Chat-v1.0"]
@pytest.mark.parametrize("model", MODELS)
@ -37,8 +37,15 @@ def test_beam_search_single_input(
beam_width, max_tokens)
for i in range(len(example_prompts)):
hf_output_ids, _ = hf_outputs[i]
vllm_output_ids, _ = vllm_outputs[i]
hf_output_ids, hf_output_texts = hf_outputs[i]
vllm_output_ids, vllm_output_texts = vllm_outputs[i]
for i, (hf_text,
vllm_text) in enumerate(zip(hf_output_texts,
vllm_output_texts)):
print(f">>>{i}-th hf output:")
print(hf_text)
print(f">>>{i}-th vllm output:")
print(vllm_text)
assert len(hf_output_ids) == len(vllm_output_ids)
for j in range(len(hf_output_ids)):
assert hf_output_ids[j] == vllm_output_ids[j], (