Remove VLLM_TEST_FORCE_FP8_MARLIN to replace with linear_backend/moe_backend (#52182)

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
Misha Goin
2026-08-18 12:58:04 -04:00
committed by GitHub
co-authored by OpenAI Codex
parent 88b2bff2c6
commit bca7bea240
15 changed files with 46 additions and 66 deletions
-6
View File
@@ -1099,12 +1099,6 @@ environment_variables: dict[str, Callable[[], Any]] = {
os.environ.get("VLLM_ALLOW_LONG_MAX_MODEL_LEN", "0").strip().lower()
in ("1", "true")
),
# If set, forces FP8 Marlin to be used for FP8 quantization regardless
# of the hardware support for FP8 compute.
"VLLM_TEST_FORCE_FP8_MARLIN": lambda: (
os.environ.get("VLLM_TEST_FORCE_FP8_MARLIN", "0").strip().lower()
in ("1", "true")
),
"VLLM_TEST_FORCE_LOAD_FORMAT": lambda: os.getenv(
"VLLM_TEST_FORCE_LOAD_FORMAT", "dummy"
),