[Quantization] Rework quantization_config to use QuantKey and allow for activation override (#41566)

This commit is contained in:
Michael Goin
2026-05-13 16:58:32 -04:00
committed by GitHub
parent cca32d55a2
commit 8efd508204
16 changed files with 621 additions and 322 deletions
+3 -4
View File
@@ -40,13 +40,12 @@ from vllm.platforms import current_platform
Fp8PerBlockOnlineLinearMethod,
Fp8PerBlockOnlineMoEMethod,
),
# quantization='online with linear_scheme_override and
# moe_scheme_override
# quantization='online' with per-layer-kind overrides
(
"online",
{
"linear_scheme_override": "fp8_per_block",
"moe_scheme_override": "fp8_per_tensor",
"linear": "fp8_per_block",
"moe": "fp8_per_tensor",
},
Fp8PerBlockOnlineLinearMethod,
Fp8PerTensorOnlineMoEMethod,