File size: 2,544 Bytes
4e51083 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | default_stage:
default_modifiers:
QuantizationModifier:
config_groups:
group_0:
targets: ['re:.*self_attn\.(q|k|v|o)_proj$', 're:.*linear_attn\.(in_proj_qkv|in_proj_z|out_proj)$',
're:.*lm_head']
weights:
num_bits: 8
type: float
symmetric: true
group_size: null
strategy: channel
block_structure: null
dynamic: false
actorder: null
scale_dtype: null
zp_dtype: null
observer: memoryless_minmax
observer_kwargs: {}
input_activations:
num_bits: 8
type: float
symmetric: true
group_size: null
strategy: token
block_structure: null
dynamic: true
actorder: null
scale_dtype: null
zp_dtype: null
observer: null
observer_kwargs: {}
output_activations: null
format: null
group_1:
targets: ['re:.*mlp\.experts\.\d+\.(gate|up|down)_proj$', 're:.*shared_expert\.(gate|up|down)_proj$']
weights:
num_bits: 4
type: float
symmetric: true
group_size: 16
strategy: tensor_group
block_structure: null
dynamic: false
actorder: null
scale_dtype: torch.float8_e4m3fn
zp_dtype: null
observer: memoryless_minmax
observer_kwargs: {}
input_activations:
num_bits: 4
type: float
symmetric: true
group_size: 16
strategy: tensor_group
block_structure: null
dynamic: local
actorder: null
scale_dtype: torch.float8_e4m3fn
zp_dtype: null
observer: static_minmax
observer_kwargs: {}
output_activations: null
format: null
targets: [Linear]
ignore: ['re:.*\.mlp\.gate$', 're:.*\.shared_expert_gate$', 're:.*\.linear_attn\.(in_proj_a|in_proj_b|norm)$',
're:.*visual.*', 're:^mtp.*']
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: static_minmax
observer_kwargs: {}
bypass_divisibility_checks: false
|