[Quantization] Rework quantization_config to use QuantKey and allow for activation override (#41566)
This commit is contained in:
@@ -103,13 +103,6 @@ def run_e2e_fusion_test(monkeypatch, caplog_mp_spawn):
|
||||
if not supports_trtllm_attention():
|
||||
matches = matches._replace(attn_quant_fusion=0)
|
||||
|
||||
# TODO: remove this after finishing migration from envs to model kwargs
|
||||
if model_name == "openai/gpt-oss-20b":
|
||||
from .common import is_blackwell
|
||||
|
||||
if is_blackwell():
|
||||
monkeypatch.setenv("VLLM_USE_FLASHINFER_MOE_MXFP4_MXFP8", "1")
|
||||
|
||||
# Disable, compile cache to make sure custom passes run.
|
||||
# Otherwise, we can't verify fusion happened through the logs.
|
||||
monkeypatch.setenv("VLLM_DISABLE_COMPILE_CACHE", "1")
|
||||
|
||||
@@ -214,4 +214,9 @@ gpt_oss_20b = ModelFusionInfo(
|
||||
sequence_parallel=n_layers * 2 + 1,
|
||||
async_tp=n_layers * 2,
|
||||
),
|
||||
model_kwargs=(
|
||||
{"quantization_config": {"moe": {"activation": "mxfp8"}}}
|
||||
if is_blackwell()
|
||||
else {}
|
||||
),
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user