-
Notifications
You must be signed in to change notification settings - Fork 0
/
deepspeed.log
209 lines (201 loc) · 46.1 KB
/
deepspeed.log
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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
[2024-01-29 01:34:20,192] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Namespace(model='meta-llama/Llama-2-13b-hf', T=100, B=1, P=32)
[2024-01-29 01:35:44,222] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed info: version=0.12.6, git-hash=unknown, git-branch=unknown
[2024-01-29 01:35:44,226] [INFO] [logging.py:96:log_dist] [Rank -1] quantize_bits = 8 mlp_extra_grouping = False, quantize_groups = 1
[1/11] /usr/local/cuda/bin/nvcc -DTORCH_EXTENSION_NAME=transformer_inference -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/includes -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/includes -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/TH -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/zhuominc/anaconda3/envs/specinfer/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_89,code=compute_89 -gencode=arch=compute_89,code=sm_89 --compiler-options '-fPIC' -O3 --use_fast_math -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -gencode=arch=compute_89,code=sm_89 -gencode=arch=compute_89,code=compute_89 -DBF16_AVAILABLE -U__CUDA_NO_BFLOAT16_OPERATORS__ -U__CUDA_NO_BFLOAT162_OPERATORS__ -c /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pointwise_ops.cu -o pointwise_ops.cuda.o
[2/11] /usr/local/cuda/bin/nvcc -DTORCH_EXTENSION_NAME=transformer_inference -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/includes -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/includes -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/TH -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/zhuominc/anaconda3/envs/specinfer/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_89,code=compute_89 -gencode=arch=compute_89,code=sm_89 --compiler-options '-fPIC' -O3 --use_fast_math -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -gencode=arch=compute_89,code=sm_89 -gencode=arch=compute_89,code=compute_89 -DBF16_AVAILABLE -U__CUDA_NO_BFLOAT16_OPERATORS__ -U__CUDA_NO_BFLOAT162_OPERATORS__ -c /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/relu.cu -o relu.cuda.o
[3/11] /usr/local/cuda/bin/nvcc -DTORCH_EXTENSION_NAME=transformer_inference -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/includes -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/includes -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/TH -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/zhuominc/anaconda3/envs/specinfer/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_89,code=compute_89 -gencode=arch=compute_89,code=sm_89 --compiler-options '-fPIC' -O3 --use_fast_math -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -gencode=arch=compute_89,code=sm_89 -gencode=arch=compute_89,code=compute_89 -DBF16_AVAILABLE -U__CUDA_NO_BFLOAT16_OPERATORS__ -U__CUDA_NO_BFLOAT162_OPERATORS__ -c /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/dequantize.cu -o dequantize.cuda.o
[4/11] /usr/local/cuda/bin/nvcc -DTORCH_EXTENSION_NAME=transformer_inference -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/includes -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/includes -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/TH -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/zhuominc/anaconda3/envs/specinfer/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_89,code=compute_89 -gencode=arch=compute_89,code=sm_89 --compiler-options '-fPIC' -O3 --use_fast_math -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -gencode=arch=compute_89,code=sm_89 -gencode=arch=compute_89,code=compute_89 -DBF16_AVAILABLE -U__CUDA_NO_BFLOAT16_OPERATORS__ -U__CUDA_NO_BFLOAT162_OPERATORS__ -c /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/transform.cu -o transform.cuda.o
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/transform.cu(38): warning #177-D: variable "d0_stride" was declared but never referenced
int d0_stride = hidden_dim * seq_length;
^
Remark: The warnings can be suppressed with "-diag-suppress <warning-number>"
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/transform.cu(66): warning #177-D: variable "lane" was declared but never referenced
int lane = d3 & 0x1f;
^
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/transform.cu(109): warning #177-D: variable "half_dim" was declared but never referenced
unsigned half_dim = (rotary_dim << 3) >> 1;
^
detected during instantiation of "void launch_bias_add_transform_0213(T *, T *, T *, const T *, const T *, int, int, unsigned int, int, int, int, int, int, __nv_bool, __nv_bool, cudaStream_t, int, int, float) [with T=__nv_bfloat16]" at line 281
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/transform.cu(110): warning #177-D: variable "d0_stride" was declared but never referenced
int d0_stride = hidden_dim * seq_length;
^
detected during instantiation of "void launch_bias_add_transform_0213(T *, T *, T *, const T *, const T *, int, int, unsigned int, int, int, int, int, int, __nv_bool, __nv_bool, cudaStream_t, int, int, float) [with T=__nv_bfloat16]" at line 281
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/transform.cu(126): warning #177-D: variable "vals_half" was declared but never referenced
T2* vals_half = reinterpret_cast<T2*>(&vals_arr);
^
detected during instantiation of "void launch_bias_add_transform_0213(T *, T *, T *, const T *, const T *, int, int, unsigned int, int, int, int, int, int, __nv_bool, __nv_bool, cudaStream_t, int, int, float) [with T=__nv_bfloat16]" at line 281
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/transform.cu(127): warning #177-D: variable "output_half" was declared but never referenced
T2* output_half = reinterpret_cast<T2*>(&output_arr);
^
detected during instantiation of "void launch_bias_add_transform_0213(T *, T *, T *, const T *, const T *, int, int, unsigned int, int, int, int, int, int, __nv_bool, __nv_bool, cudaStream_t, int, int, float) [with T=__nv_bfloat16]" at line 281
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/transform.cu(144): warning #177-D: variable "lane" was declared but never referenced
int lane = d3 & 0x1f;
^
detected during instantiation of "void launch_bias_add_transform_0213(T *, T *, T *, const T *, const T *, int, int, unsigned int, int, int, int, int, int, __nv_bool, __nv_bool, cudaStream_t, int, int, float) [with T=__nv_bfloat16]" at line 281
[5/11] /usr/local/cuda/bin/nvcc -DTORCH_EXTENSION_NAME=transformer_inference -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/includes -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/includes -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/TH -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/zhuominc/anaconda3/envs/specinfer/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_89,code=compute_89 -gencode=arch=compute_89,code=sm_89 --compiler-options '-fPIC' -O3 --use_fast_math -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -gencode=arch=compute_89,code=sm_89 -gencode=arch=compute_89,code=compute_89 -DBF16_AVAILABLE -U__CUDA_NO_BFLOAT16_OPERATORS__ -U__CUDA_NO_BFLOAT162_OPERATORS__ -c /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/gelu.cu -o gelu.cuda.o
[6/11] /usr/local/cuda/bin/nvcc -DTORCH_EXTENSION_NAME=transformer_inference -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/includes -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/includes -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/TH -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/zhuominc/anaconda3/envs/specinfer/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_89,code=compute_89 -gencode=arch=compute_89,code=sm_89 --compiler-options '-fPIC' -O3 --use_fast_math -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -gencode=arch=compute_89,code=sm_89 -gencode=arch=compute_89,code=compute_89 -DBF16_AVAILABLE -U__CUDA_NO_BFLOAT16_OPERATORS__ -U__CUDA_NO_BFLOAT162_OPERATORS__ -c /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/apply_rotary_pos_emb.cu -o apply_rotary_pos_emb.cuda.o
[7/11] /usr/local/cuda/bin/nvcc -DTORCH_EXTENSION_NAME=transformer_inference -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/includes -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/includes -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/TH -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/zhuominc/anaconda3/envs/specinfer/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_89,code=compute_89 -gencode=arch=compute_89,code=sm_89 --compiler-options '-fPIC' -O3 --use_fast_math -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -gencode=arch=compute_89,code=sm_89 -gencode=arch=compute_89,code=compute_89 -DBF16_AVAILABLE -U__CUDA_NO_BFLOAT16_OPERATORS__ -U__CUDA_NO_BFLOAT162_OPERATORS__ -c /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/rms_norm.cu -o rms_norm.cuda.o
[8/11] /usr/local/cuda/bin/nvcc -DTORCH_EXTENSION_NAME=transformer_inference -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/includes -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/includes -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/TH -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/zhuominc/anaconda3/envs/specinfer/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_89,code=compute_89 -gencode=arch=compute_89,code=sm_89 --compiler-options '-fPIC' -O3 --use_fast_math -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -gencode=arch=compute_89,code=sm_89 -gencode=arch=compute_89,code=compute_89 -DBF16_AVAILABLE -U__CUDA_NO_BFLOAT16_OPERATORS__ -U__CUDA_NO_BFLOAT162_OPERATORS__ -c /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/softmax.cu -o softmax.cuda.o
[9/11] /usr/local/cuda/bin/nvcc -DTORCH_EXTENSION_NAME=transformer_inference -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/includes -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/includes -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/TH -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/zhuominc/anaconda3/envs/specinfer/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_89,code=compute_89 -gencode=arch=compute_89,code=sm_89 --compiler-options '-fPIC' -O3 --use_fast_math -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -gencode=arch=compute_89,code=sm_89 -gencode=arch=compute_89,code=compute_89 -DBF16_AVAILABLE -U__CUDA_NO_BFLOAT16_OPERATORS__ -U__CUDA_NO_BFLOAT162_OPERATORS__ -c /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/layer_norm.cu -o layer_norm.cuda.o
[10/11] c++ -MMD -MF pt_binding.o.d -DTORCH_EXTENSION_NAME=transformer_inference -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/includes -I/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/includes -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/TH -isystem /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/zhuominc/anaconda3/envs/specinfer/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17 -O3 -std=c++17 -g -Wno-reorder -DBF16_AVAILABLE -c /home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp -o pt_binding.o
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp: In instantiation of ‘std::vector<at::Tensor> ds_softmax_context(at::Tensor&, at::Tensor&, int, bool, bool, int, int, float, bool, bool, int, bool, unsigned int, unsigned int, at::Tensor&, float) [with T = float]’:
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:2015:5: required from here
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:541:50: warning: narrowing conversion of ‘(((size_t)hidden_dim) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
541 | {hidden_dim * InferenceContext::Instance().GetMaxTokenLength(),
| ~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:541:50: warning: narrowing conversion of ‘(((size_t)hidden_dim) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:542:41: warning: narrowing conversion of ‘(((size_t)k) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
542 | k * InferenceContext::Instance().GetMaxTokenLength(),
| ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:542:41: warning: narrowing conversion of ‘(((size_t)k) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:550:38: warning: narrowing conversion of ‘(((size_t)hidden_dim) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
550 | {hidden_dim * InferenceContext::Instance().GetMaxTokenLength(),
| ~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:550:38: warning: narrowing conversion of ‘(((size_t)hidden_dim) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:551:29: warning: narrowing conversion of ‘(((size_t)k) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
551 | k * InferenceContext::Instance().GetMaxTokenLength(),
| ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:551:29: warning: narrowing conversion of ‘(((size_t)k) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp: In instantiation of ‘std::vector<at::Tensor> ds_rms_mlp_gemm(at::Tensor&, at::Tensor&, at::Tensor&, at::Tensor&, at::Tensor&, float, at::Tensor&, at::Tensor&, bool, int, bool) [with T = float]’:
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:2015:5: required from here
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:1581:72: warning: narrowing conversion of ‘(size_t)mlp_1_out_neurons’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
1581 | at::from_blob(intermediate_ptr, {input.size(0), input.size(1), mlp_1_out_neurons}, options);
| ^~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:1581:72: warning: narrowing conversion of ‘mlp_1_out_neurons’ from ‘const size_t’ {aka ‘const long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp: In instantiation of ‘std::vector<at::Tensor> ds_softmax_context(at::Tensor&, at::Tensor&, int, bool, bool, int, int, float, bool, bool, int, bool, unsigned int, unsigned int, at::Tensor&, float) [with T = __half]’:
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:2016:5: required from here
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:541:50: warning: narrowing conversion of ‘(((size_t)hidden_dim) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
541 | {hidden_dim * InferenceContext::Instance().GetMaxTokenLength(),
| ~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:541:50: warning: narrowing conversion of ‘(((size_t)hidden_dim) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:542:41: warning: narrowing conversion of ‘(((size_t)k) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
542 | k * InferenceContext::Instance().GetMaxTokenLength(),
| ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:542:41: warning: narrowing conversion of ‘(((size_t)k) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:550:38: warning: narrowing conversion of ‘(((size_t)hidden_dim) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
550 | {hidden_dim * InferenceContext::Instance().GetMaxTokenLength(),
| ~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:550:38: warning: narrowing conversion of ‘(((size_t)hidden_dim) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:551:29: warning: narrowing conversion of ‘(((size_t)k) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
551 | k * InferenceContext::Instance().GetMaxTokenLength(),
| ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:551:29: warning: narrowing conversion of ‘(((size_t)k) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp: In instantiation of ‘std::vector<at::Tensor> ds_rms_mlp_gemm(at::Tensor&, at::Tensor&, at::Tensor&, at::Tensor&, at::Tensor&, float, at::Tensor&, at::Tensor&, bool, int, bool) [with T = __half]’:
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:2016:5: required from here
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:1581:72: warning: narrowing conversion of ‘(size_t)mlp_1_out_neurons’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
1581 | at::from_blob(intermediate_ptr, {input.size(0), input.size(1), mlp_1_out_neurons}, options);
| ^~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:1581:72: warning: narrowing conversion of ‘mlp_1_out_neurons’ from ‘const size_t’ {aka ‘const long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp: In instantiation of ‘std::vector<at::Tensor> ds_softmax_context(at::Tensor&, at::Tensor&, int, bool, bool, int, int, float, bool, bool, int, bool, unsigned int, unsigned int, at::Tensor&, float) [with T = __nv_bfloat16]’:
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:2018:5: required from here
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:541:50: warning: narrowing conversion of ‘(((size_t)hidden_dim) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
541 | {hidden_dim * InferenceContext::Instance().GetMaxTokenLength(),
| ~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:541:50: warning: narrowing conversion of ‘(((size_t)hidden_dim) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:542:41: warning: narrowing conversion of ‘(((size_t)k) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
542 | k * InferenceContext::Instance().GetMaxTokenLength(),
| ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:542:41: warning: narrowing conversion of ‘(((size_t)k) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:550:38: warning: narrowing conversion of ‘(((size_t)hidden_dim) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
550 | {hidden_dim * InferenceContext::Instance().GetMaxTokenLength(),
| ~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:550:38: warning: narrowing conversion of ‘(((size_t)hidden_dim) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:551:29: warning: narrowing conversion of ‘(((size_t)k) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
551 | k * InferenceContext::Instance().GetMaxTokenLength(),
| ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:551:29: warning: narrowing conversion of ‘(((size_t)k) * (& InferenceContext::Instance())->InferenceContext::GetMaxTokenLength())’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp: In instantiation of ‘std::vector<at::Tensor> ds_rms_mlp_gemm(at::Tensor&, at::Tensor&, at::Tensor&, at::Tensor&, at::Tensor&, float, at::Tensor&, at::Tensor&, bool, int, bool) [with T = __nv_bfloat16]’:
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:2018:5: required from here
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:1581:72: warning: narrowing conversion of ‘(size_t)mlp_1_out_neurons’ from ‘size_t’ {aka ‘long unsigned int’} to ‘long int’ [-Wnarrowing]
1581 | at::from_blob(intermediate_ptr, {input.size(0), input.size(1), mlp_1_out_neurons}, options);
| ^~~~~~~~~~~~~~~~~
/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/deepspeed/ops/csrc/transformer/inference/csrc/pt_binding.cpp:1581:72: warning: narrowing conversion of ‘mlp_1_out_neurons’ from ‘const size_t’ {aka ‘const long unsigned int’} to ‘long int’ [-Wnarrowing]
[11/11] c++ pt_binding.o gelu.cuda.o relu.cuda.o layer_norm.cuda.o rms_norm.cuda.o softmax.cuda.o dequantize.cuda.o apply_rotary_pos_emb.cuda.o transform.cuda.o pointwise_ops.cuda.o -shared -lcurand -L/home/zhuominc/anaconda3/envs/specinfer/lib/python3.9/site-packages/torch/lib -lc10 -lc10_cuda -ltorch_cpu -ltorch_cuda -ltorch -ltorch_python -L/usr/local/cuda/lib64 -lcudart -o transformer_inference.so
Time to load transformer_inference op: 33.93190145492554 seconds
[2024-01-29 01:36:19,712] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed-Inference config: {'layer_id': 0, 'hidden_size': 5120, 'intermediate_size': 13824, 'heads': 40, 'num_hidden_layers': -1, 'dtype': torch.float16, 'pre_layer_norm': True, 'norm_type': <NormType.RMSNorm: 3>, 'local_rank': -1, 'stochastic_mode': False, 'epsilon': 1e-05, 'mp_size': 1, 'scale_attention': True, 'triangular_masking': True, 'local_attention': False, 'window_size': 1, 'rotary_dim': 128, 'rotate_half': True, 'rotate_every_two': False, 'return_tuple': True, 'mlp_after_attn': True, 'mlp_act_func_type': <ActivationFuncType.GATED_SILU: 4>, 'specialized_mode': False, 'training_mp_size': 1, 'bigscience_bloom': False, 'max_out_tokens': 1024, 'min_out_tokens': 1, 'scale_attn_by_inverse_layer_idx': False, 'enable_qkv_quantization': False, 'use_mup': False, 'return_single_tuple': False, 'set_empty_params': False, 'transposed_mode': False, 'use_triton': False, 'triton_autotune': False, 'num_kv': -1, 'rope_theta': 10000.0}
Length :32, inference time:0.03897541046142578
------------------------------------------------------
Free memory : 17.995911 (GigaBytes)
Total memory: 44.318970 (GigaBytes)
Requested memory: 1.914062 (GigaBytes)
Setting maximum total tokens (input + output) to 1024
WorkSpace: 0x7fad92000000
------------------------------------------------------
[2024-01-29 01:36:53,167] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Namespace(model='meta-llama/Llama-2-13b-hf', T=100, B=1, P=64)
[2024-01-29 01:38:16,970] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed info: version=0.12.6, git-hash=unknown, git-branch=unknown
[2024-01-29 01:38:16,973] [INFO] [logging.py:96:log_dist] [Rank -1] quantize_bits = 8 mlp_extra_grouping = False, quantize_groups = 1
ninja: no work to do.
Time to load transformer_inference op: 0.3224673271179199 seconds
[2024-01-29 01:38:18,752] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed-Inference config: {'layer_id': 0, 'hidden_size': 5120, 'intermediate_size': 13824, 'heads': 40, 'num_hidden_layers': -1, 'dtype': torch.float16, 'pre_layer_norm': True, 'norm_type': <NormType.RMSNorm: 3>, 'local_rank': -1, 'stochastic_mode': False, 'epsilon': 1e-05, 'mp_size': 1, 'scale_attention': True, 'triangular_masking': True, 'local_attention': False, 'window_size': 1, 'rotary_dim': 128, 'rotate_half': True, 'rotate_every_two': False, 'return_tuple': True, 'mlp_after_attn': True, 'mlp_act_func_type': <ActivationFuncType.GATED_SILU: 4>, 'specialized_mode': False, 'training_mp_size': 1, 'bigscience_bloom': False, 'max_out_tokens': 1024, 'min_out_tokens': 1, 'scale_attn_by_inverse_layer_idx': False, 'enable_qkv_quantization': False, 'use_mup': False, 'return_single_tuple': False, 'set_empty_params': False, 'transposed_mode': False, 'use_triton': False, 'triton_autotune': False, 'num_kv': -1, 'rope_theta': 10000.0}
Length :64, inference time:0.040507111549377445
------------------------------------------------------
Free memory : 17.995911 (GigaBytes)
Total memory: 44.318970 (GigaBytes)
Requested memory: 1.914062 (GigaBytes)
Setting maximum total tokens (input + output) to 1024
WorkSpace: 0x7f74ba000000
------------------------------------------------------
[2024-01-29 01:38:52,205] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Namespace(model='meta-llama/Llama-2-13b-hf', T=100, B=1, P=128)
[2024-01-29 01:40:15,968] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed info: version=0.12.6, git-hash=unknown, git-branch=unknown
[2024-01-29 01:40:15,972] [INFO] [logging.py:96:log_dist] [Rank -1] quantize_bits = 8 mlp_extra_grouping = False, quantize_groups = 1
ninja: no work to do.
Time to load transformer_inference op: 0.3483414649963379 seconds
[2024-01-29 01:40:17,782] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed-Inference config: {'layer_id': 0, 'hidden_size': 5120, 'intermediate_size': 13824, 'heads': 40, 'num_hidden_layers': -1, 'dtype': torch.float16, 'pre_layer_norm': True, 'norm_type': <NormType.RMSNorm: 3>, 'local_rank': -1, 'stochastic_mode': False, 'epsilon': 1e-05, 'mp_size': 1, 'scale_attention': True, 'triangular_masking': True, 'local_attention': False, 'window_size': 1, 'rotary_dim': 128, 'rotate_half': True, 'rotate_every_two': False, 'return_tuple': True, 'mlp_after_attn': True, 'mlp_act_func_type': <ActivationFuncType.GATED_SILU: 4>, 'specialized_mode': False, 'training_mp_size': 1, 'bigscience_bloom': False, 'max_out_tokens': 1024, 'min_out_tokens': 1, 'scale_attn_by_inverse_layer_idx': False, 'enable_qkv_quantization': False, 'use_mup': False, 'return_single_tuple': False, 'set_empty_params': False, 'transposed_mode': False, 'use_triton': False, 'triton_autotune': False, 'num_kv': -1, 'rope_theta': 10000.0}
Length :128, inference time:0.04441212415695191
------------------------------------------------------
Free memory : 17.995911 (GigaBytes)
Total memory: 44.318970 (GigaBytes)
Requested memory: 1.914062 (GigaBytes)
Setting maximum total tokens (input + output) to 1024
WorkSpace: 0x7fa872000000
------------------------------------------------------
[2024-01-29 01:40:51,787] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Namespace(model='meta-llama/Llama-2-13b-hf', T=100, B=1, P=192)
[2024-01-29 01:42:28,477] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Namespace(model='meta-llama/Llama-2-7b-hf', T=100, B=1, P=32)
[2024-01-29 01:43:12,202] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed info: version=0.12.6, git-hash=unknown, git-branch=unknown
[2024-01-29 01:43:12,205] [INFO] [logging.py:96:log_dist] [Rank -1] quantize_bits = 8 mlp_extra_grouping = False, quantize_groups = 1
ninja: no work to do.
Time to load transformer_inference op: 0.23725199699401855 seconds
[2024-01-29 01:43:13,514] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed-Inference config: {'layer_id': 0, 'hidden_size': 4096, 'intermediate_size': 11008, 'heads': 32, 'num_hidden_layers': -1, 'dtype': torch.float16, 'pre_layer_norm': True, 'norm_type': <NormType.RMSNorm: 3>, 'local_rank': -1, 'stochastic_mode': False, 'epsilon': 1e-05, 'mp_size': 1, 'scale_attention': True, 'triangular_masking': True, 'local_attention': False, 'window_size': 1, 'rotary_dim': 128, 'rotate_half': True, 'rotate_every_two': False, 'return_tuple': True, 'mlp_after_attn': True, 'mlp_act_func_type': <ActivationFuncType.GATED_SILU: 4>, 'specialized_mode': False, 'training_mp_size': 1, 'bigscience_bloom': False, 'max_out_tokens': 1024, 'min_out_tokens': 1, 'scale_attn_by_inverse_layer_idx': False, 'enable_qkv_quantization': False, 'use_mup': False, 'return_single_tuple': False, 'set_empty_params': False, 'transposed_mode': False, 'use_triton': False, 'triton_autotune': False, 'num_kv': -1, 'rope_theta': 10000.0}
Length :32, inference time:0.020939748287200927
------------------------------------------------------
Free memory : 30.365051 (GigaBytes)
Total memory: 44.318970 (GigaBytes)
Requested memory: 1.281250 (GigaBytes)
Setting maximum total tokens (input + output) to 1024
WorkSpace: 0x7f9d40000000
------------------------------------------------------
[2024-01-29 01:43:32,842] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Namespace(model='meta-llama/Llama-2-7b-hf', T=100, B=1, P=64)
[2024-01-29 01:44:16,872] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed info: version=0.12.6, git-hash=unknown, git-branch=unknown
[2024-01-29 01:44:16,875] [INFO] [logging.py:96:log_dist] [Rank -1] quantize_bits = 8 mlp_extra_grouping = False, quantize_groups = 1
ninja: no work to do.
Time to load transformer_inference op: 0.2516777515411377 seconds
[2024-01-29 01:44:18,220] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed-Inference config: {'layer_id': 0, 'hidden_size': 4096, 'intermediate_size': 11008, 'heads': 32, 'num_hidden_layers': -1, 'dtype': torch.float16, 'pre_layer_norm': True, 'norm_type': <NormType.RMSNorm: 3>, 'local_rank': -1, 'stochastic_mode': False, 'epsilon': 1e-05, 'mp_size': 1, 'scale_attention': True, 'triangular_masking': True, 'local_attention': False, 'window_size': 1, 'rotary_dim': 128, 'rotate_half': True, 'rotate_every_two': False, 'return_tuple': True, 'mlp_after_attn': True, 'mlp_act_func_type': <ActivationFuncType.GATED_SILU: 4>, 'specialized_mode': False, 'training_mp_size': 1, 'bigscience_bloom': False, 'max_out_tokens': 1024, 'min_out_tokens': 1, 'scale_attn_by_inverse_layer_idx': False, 'enable_qkv_quantization': False, 'use_mup': False, 'return_single_tuple': False, 'set_empty_params': False, 'transposed_mode': False, 'use_triton': False, 'triton_autotune': False, 'num_kv': -1, 'rope_theta': 10000.0}
Length :64, inference time:0.021544628143310547
------------------------------------------------------
Free memory : 30.365051 (GigaBytes)
Total memory: 44.318970 (GigaBytes)
Requested memory: 1.281250 (GigaBytes)
Setting maximum total tokens (input + output) to 1024
WorkSpace: 0x7fd214000000
------------------------------------------------------
[2024-01-29 01:44:38,016] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Namespace(model='meta-llama/Llama-2-7b-hf', T=100, B=1, P=128)
[2024-01-29 01:45:21,995] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed info: version=0.12.6, git-hash=unknown, git-branch=unknown
[2024-01-29 01:45:21,998] [INFO] [logging.py:96:log_dist] [Rank -1] quantize_bits = 8 mlp_extra_grouping = False, quantize_groups = 1
ninja: no work to do.
Time to load transformer_inference op: 0.26516246795654297 seconds
[2024-01-29 01:45:23,319] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed-Inference config: {'layer_id': 0, 'hidden_size': 4096, 'intermediate_size': 11008, 'heads': 32, 'num_hidden_layers': -1, 'dtype': torch.float16, 'pre_layer_norm': True, 'norm_type': <NormType.RMSNorm: 3>, 'local_rank': -1, 'stochastic_mode': False, 'epsilon': 1e-05, 'mp_size': 1, 'scale_attention': True, 'triangular_masking': True, 'local_attention': False, 'window_size': 1, 'rotary_dim': 128, 'rotate_half': True, 'rotate_every_two': False, 'return_tuple': True, 'mlp_after_attn': True, 'mlp_act_func_type': <ActivationFuncType.GATED_SILU: 4>, 'specialized_mode': False, 'training_mp_size': 1, 'bigscience_bloom': False, 'max_out_tokens': 1024, 'min_out_tokens': 1, 'scale_attn_by_inverse_layer_idx': False, 'enable_qkv_quantization': False, 'use_mup': False, 'return_single_tuple': False, 'set_empty_params': False, 'transposed_mode': False, 'use_triton': False, 'triton_autotune': False, 'num_kv': -1, 'rope_theta': 10000.0}
Length :128, inference time:0.022522497177124023
------------------------------------------------------
Free memory : 30.365051 (GigaBytes)
Total memory: 44.318970 (GigaBytes)
Requested memory: 1.281250 (GigaBytes)
Setting maximum total tokens (input + output) to 1024
WorkSpace: 0x7f36bc000000
------------------------------------------------------