[Quantization] Rework quantization_config to use QuantKey and allow for activation override (#41566)
This commit is contained in:
@@ -3,6 +3,4 @@
|
||||
model_name: "openai/gpt-oss-20b"
|
||||
metric_threshold: 0.568
|
||||
reasoning_effort: "low"
|
||||
server_args: "--tensor-parallel-size 2"
|
||||
env:
|
||||
VLLM_USE_FLASHINFER_MOE_MXFP4_MXFP8_CUTLASS: "1"
|
||||
server_args: "--tensor-parallel-size 2 --moe-backend flashinfer_cutlass --quantization-config.moe.activation mxfp8"
|
||||
|
||||
@@ -3,6 +3,4 @@
|
||||
model_name: "openai/gpt-oss-20b"
|
||||
metric_threshold: 0.568
|
||||
reasoning_effort: "low"
|
||||
server_args: "--tensor-parallel-size 2"
|
||||
env:
|
||||
VLLM_USE_FLASHINFER_MOE_MXFP4_MXFP8: "1"
|
||||
server_args: "--tensor-parallel-size 2 --quantization-config.moe.activation mxfp8"
|
||||
|
||||
Reference in New Issue
Block a user