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

[Attention] Update tests to remove deprecated env vars (#30563)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2025-12-17 12:49:59 -05:00
committed by GitHub
parent 9ca8cb38fd
commit 7eb6cb6c18
34 changed files with 580 additions and 447 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/models/quantization/test_fp8.py
View File

@@ -75,7 +75,6 @@ def test_models(
with monkeypatch.context() as m:
m.setenv("TOKENIZERS_PARALLELISM", "true")
m.setenv("VLLM_ATTENTION_BACKEND", backend)
MAX_MODEL_LEN = 1024
NUM_LOG_PROBS = 8
@@ -86,6 +85,7 @@ def test_models(
tensor_parallel_size=tensor_parallel_size,
enforce_eager=enforce_eager,
kv_cache_dtype="auto",
attention_config={"backend": backend},
) as vllm_model:
baseline_outputs = vllm_model.generate_greedy_logprobs(
example_prompts, max_tokens, NUM_LOG_PROBS
@@ -97,6 +97,7 @@ def test_models(
tensor_parallel_size=tensor_parallel_size,
enforce_eager=enforce_eager,
kv_cache_dtype=kv_cache_dtype,
attention_config={"backend": backend},
) as vllm_model:
test_outputs = vllm_model.generate_greedy_logprobs(
example_prompts, max_tokens, NUM_LOG_PROBS