[Quantization] Consolidate experts_int8 with fp8 online quantization (#38463)

Signed-off-by: Josephasafg <ajgard7@gmail.com>
This commit is contained in:
Asaf Gardin
2026-04-16 13:12:20 -07:00
committed by GitHub
parent b897f00c9c
commit ad2b1277f9
9 changed files with 403 additions and 313 deletions
-1
View File
@@ -38,6 +38,5 @@ def test_model_experts_int8_startup(
dtype=dtype,
enforce_eager=True,
quantization="experts_int8",
allow_deprecated_quantization=True,
) as vllm_model:
vllm_model.generate_greedy(example_prompts, max_tokens)