pshashid's picture
Upload NVFP4 quantized model with FP8 KV-cache
0f97414 verified
default_stage:
default_modifiers:
QuantizationModifier:
targets: [Linear]
ignore: [lm_head]
scheme: NVFP4
kv_cache_scheme:
num_bits: 8
type: float
symmetric: true
group_size: null
strategy: tensor
block_structure: null
dynamic: false
actorder: null
scale_dtype: null
zp_dtype: null
observer: memoryless_minmax
observer_kwargs: {}
bypass_divisibility_checks: false