Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
DeepSeek-V2-Lite-Chat-sft-amx-multi-gpu.yaml 4.45 KB
Newer Older
shihm's avatar
uodata  
shihm committed
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
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139 
- match:
    name: "^model.embed_tokens"
  replace:
    class: "default"
    kwargs:
        generate_device: "cpu"
        prefill_device: "cpu"

- match:
    name: "^model\\.layers\\.(0|[1-9])\\."
    class: ktransformers.models.modeling_deepseek.DeepseekV2YarnRotaryEmbedding
  replace:
    class: ktransformers.operators.RoPE.YarnRotaryEmbedding
    kwargs:
      generate_device: "cuda:0"
      prefill_device: "cuda:0"
- match:
    name: "^model\\.layers\\.([12][0-9])\\."
    class: ktransformers.models.modeling_deepseek.DeepseekV2YarnRotaryEmbedding
  replace:
    class: ktransformers.operators.RoPE.YarnRotaryEmbedding
    kwargs:
      generate_device: "cuda:1"
      prefill_device: "cuda:1"

- match:
    name: "^model\\.layers\\.(0|[1-9])\\.(?!.*self_attn\\.kv_b_proj).*$"  # regular expression
    class: torch.nn.Linear  # only match modules matching name and class simultaneously
  replace:
    class: ktransformers.operators.linear.KTransformersLinear  # optimized Kernel on quantized data types
    kwargs:
      generate_device: "cuda:0"
      prefill_device: "cuda:0"
      generate_op: "KLinearTorch"
      prefill_op: "KLinearTorch"

- match:
    name: "^model\\.layers\\.([12][0-9])\\.(?!.*self_attn\\.kv_b_proj).*$"  # regular expression
    class: torch.nn.Linear  # only match modules matching name and class simultaneously
  replace:
    class: ktransformers.operators.linear.KTransformersLinear  # optimized Kernel on quantized data types
    kwargs:
      generate_device: "cuda:1"
      prefill_device: "cuda:1"
      generate_op: "KLinearTorch"
      prefill_op: "KLinearTorch"

- match:
    name: "^model\\.layers\\.(0|[1-9])\\.mlp$"
    class: ktransformers.models.modeling_deepseek.DeepseekV2MoE
  replace:
    class: ktransformers.operators.experts.KDeepseekV2MoE     # mlp module with custom forward function
    kwargs:
      generate_device: "cuda:0"
      prefill_device: "cuda:0"
- match:
    name: "^model\\.layers\\.([12][0-9])\\.mlp$"
    class: ktransformers.models.modeling_deepseek.DeepseekV2MoE
  replace:
    class: ktransformers.operators.experts.KDeepseekV2MoE     # mlp module with custom forward function
    kwargs:
      generate_device: "cuda:1"
      prefill_device: "cuda:1"

- match:
    name: "^model\\.layers\\.(0|[1-9])\\.mlp\\.experts$"
  replace:
    class: ktransformers.operators.experts.KTransformersExperts     # custom MoE Kernel with expert paralleism
    kwargs:
      prefill_device: "cuda:0"
      prefill_op: "KExpertsTorch"
      generate_device: "cpu"
      generate_op:  "KSFTExpertsCPU"
      out_device: "cuda:0"
      backend: "AMXInt8" # or "AMXBF16" or "llamafile" (default)
  recursive: False # don't recursively inject submodules of this module

- match:
    name: "^model\\.layers\\.([12][0-9])\\.mlp\\.experts$"
  replace:
    class: ktransformers.operators.experts.KTransformersExperts     # custom MoE Kernel with expert paralleism
    kwargs:
      prefill_device: "cuda:1"
      prefill_op: "KExpertsTorch"
      generate_device: "cpu"
      generate_op:  "KSFTExpertsCPU"
      out_device: "cuda:1"
      backend: "AMXInt8" # or "AMXBF16" or "llamafile" (default)
  recursive: False # don't recursively inject submodules of this module

- match:
    name: "^model\\.layers\\.(0|[1-9])\\.self_attn$"
  replace:
    class: ktransformers.operators.attention.KDeepseekV2Attention # optimized MLA implementation
    kwargs:
      generate_device: "cuda:0"
      prefill_device: "cuda:0"
- match:
    name: "^model\\.layers\\.([12][0-9])\\.self_attn$"
  replace:
    class: ktransformers.operators.attention.KDeepseekV2Attention # optimized MLA implementation
    kwargs:
      generate_device: "cuda:1"
      prefill_device: "cuda:1"
- match:
    name: "^model$"
  replace:
    class: "ktransformers.operators.models.KDeepseekV2Model"
    kwargs:
      per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
      transfer_map:
        10: "cuda:1"

- match:
    name: "^model\\.layers\\.(0|[1-9])\\."
  replace:
    class: "default"
    kwargs:
      generate_device: "cuda:0"
      prefill_device: "cuda:0"

- match:
    name: "^lm_head"
    class: torch.nn.Linear
  replace:
    class: ktransformers.operators.linear.KTransformersLinear
    kwargs:
      generate_device: "cuda:1"
      prefill_device: "cuda:1"
      generate_op: "KLinearTorch"
      prefill_op: "KLinearTorch"

- match:
    name: "(^model\\.layers\\.([12][0-9])\\.)|(model.norm)"
  replace:
    class: "default"
    kwargs:
      generate_device: "cuda:1"
      prefill_device: "cuda:1"