[CI Sprint] Quantization CI Cleanup (#24130)

Signed-off-by: Alex Yun <alexyun04@gmail.com>
This commit is contained in:
Alex
2025-11-18 08:21:48 -06:00
committed by GitHub
parent 184b12fdc6
commit f6aa122698
10 changed files with 32 additions and 26 deletions

View File

@@ -38,6 +38,7 @@ def test_ptpc_fp8_rocm(vllm_runner, dtype: str, kv_cache_dtype: str) -> None:
"facebook/opt-125m",
dtype=dtype,
quantization="ptpc_fp8",
enforce_eager=True,
kv_cache_dtype=kv_cache_dtype,
)
except AssertionError as e:
@@ -65,5 +66,5 @@ def test_ptpc_fp8_rocm(vllm_runner, dtype: str, kv_cache_dtype: str) -> None:
llm.apply_model(check_model)
output = llm.generate_greedy("Hello my name is", max_tokens=20)
output = llm.generate_greedy("Hello my name is", max_tokens=4)
assert output