xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 08:25:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI][Spec Decode] Adjust threshold for flaky ngram spec decoding test again (#24771)

Browse Source 
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
This commit is contained in:
Wenlong Wang 2025-09-13 00:45:11 -07:00 committed by GitHub
parent 41ae4a1eab
commit cfa3234a5b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tests/v1/e2e/test_spec_decode.py
View File

@ -117,9 +117,9 @@ def test_ngram_correctness(
print(f"ref_output: {ref_output.outputs[0].text}")
print(f"spec_output: {spec_output.outputs[0].text}")
# Heuristic: expect at least 68% of the prompts to match exactly
# Heuristic: expect at least 66% of the prompts to match exactly
# Upon failure, inspect the outputs to check for inaccuracy.
assert matches >= int(0.68 * len(ref_outputs))
assert matches >= int(0.66 * len(ref_outputs))
del spec_llm
torch.cuda.empty_cache()
cleanup_dist_env_and_memory()