-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtemp.txt
136 lines (128 loc) · 10.7 KB
/
temp.txt
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
time=2024-06-26T08:50:37.145+02:00 level=INFO source=types.go:71 msg="inference compute" id=0 library=rocm compute=gfx1030 driver=0.0 name=1002:73bf total="16.0 GiB" available="16.0 GiB"
2024/06/26 08:50:55 routes.go:1064: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:10m OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:2 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:/ollama OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:2 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-06-26T08:50:55.944+02:00 level=INFO source=images.go:730 msg="total blobs: 108"
time=2024-06-26T08:50:55.947+02:00 level=INFO source=images.go:737 msg="total unused blobs removed: 0"
time=2024-06-26T08:50:55.948+02:00 level=INFO source=routes.go:1111 msg="Listening on [::]:11434 (version 0.1.46)"
time=2024-06-26T08:50:55.948+02:00 level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama1305881221/runners
time=2024-06-26T08:50:59.090+02:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11 rocm_v60101]"
time=2024-06-26T08:50:59.112+02:00 level=WARN source=amd_linux.go:58 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"
time=2024-06-26T08:50:59.120+02:00 level=INFO source=amd_linux.go:330 msg="amdgpu is supported" gpu=0 gpu_type=gfx1030
time=2024-06-26T08:50:59.121+02:00 level=INFO source=types.go:98 msg="inference compute" id=0 library=rocm compute=gfx1030 driver=0.0 name=1002:73bf total="16.0 GiB" available="16.0 GiB"
time=2024-06-26T08:51:10.626+02:00 level=WARN source=types.go:430 msg="invalid option provided" option=""
time=2024-06-26T08:51:10.640+02:00 level=INFO source=memory.go:309 msg="offload to rocm" layers.requested=-1 layers.model=33 layers.offload=23 layers.split="" memory.available="[16.0 GiB]" memory.required.full="20.9 GiB" memory.required.partial="15.6 GiB" memory.required.kv="2.0 GiB" memory.required.allocations="[15.6 GiB]" memory.weights.total="17.8 GiB" memory.weights.repeating="17.5 GiB" memory.weights.nonrepeating="250.0 MiB" memory.graph.full="1.1 GiB" memory.graph.partial="1.8 GiB"
time=2024-06-26T08:51:10.645+02:00 level=INFO source=server.go:368 msg="starting llama server" cmd="/tmp/ollama1305881221/runners/rocm_v60101/ollama_llama_server --model /ollama/blobs/sha256-cd9ae73d8328beff1097f313f8787302d476647ed9f56deba7000d6d4633d277 --ctx-size 16384 --batch-size 512 --embedding --log-disable --n-gpu-layers 23 --no-mmap --parallel 2 --port 40153"
time=2024-06-26T08:51:10.646+02:00 level=INFO source=sched.go:382 msg="loaded runners" count=1
time=2024-06-26T08:51:10.646+02:00 level=INFO source=server.go:556 msg="waiting for llama runner to start responding"
time=2024-06-26T08:51:10.646+02:00 level=INFO source=server.go:594 msg="waiting for server to become available" status="llm server error"
llama_model_loader: loaded meta data with 26 key-value pairs and 611 tensors from /ollama/blobs/sha256-cd9ae73d8328beff1097f313f8787302d476647ed9f56deba7000d6d4633d277 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.name str = .
llama_model_loader: - kv 2: llama.context_length u32 = 32768
llama_model_loader: - kv 3: llama.embedding_length u32 = 4096
llama_model_loader: - kv 4: llama.block_count u32 = 32
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 7: llama.attention.head_count u32 = 32
llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 9: llama.expert_count u32 = 4
llama_model_loader: - kv 10: llama.expert_used_count u32 = 2
llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 12: llama.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 13: general.file_type u32 = 17
llama_model_loader: - kv 14: tokenizer.ggml.model str = llama
llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv 16: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 20: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 1
llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 24: tokenizer.chat_template str = {% for message in messages %}{{bos_to...
llama_model_loader: - kv 25: general.quantization_version u32 = 2
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type f16: 33 tensors
llama_model_loader: - type q5_K: 433 tensors
llama_model_loader: - type q6_K: 80 tensors
llm_load_vocab: special tokens cache size = 259
llm_load_vocab: token to piece cache size = 0.1637 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32000
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 32768
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 4
llm_load_print_meta: n_embd_k_gqa = 1024
llm_load_print_meta: n_embd_v_gqa = 1024
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale = 0.0e+00
llm_load_print_meta: n_ff = 14336
llm_load_print_meta: n_expert = 4
llm_load_print_meta: n_expert_used = 2
llm_load_print_meta: causal attn = 1
llm_load_print_meta: pooling type = 0
llm_load_print_meta: rope type = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn = 32768
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: ssm_d_conv = 0
llm_load_print_meta: ssm_d_inner = 0
llm_load_print_meta: ssm_d_state = 0
llm_load_print_meta: ssm_dt_rank = 0
llm_load_print_meta: model type = 7B
llm_load_print_meta: model ftype = Q5_K - Medium
llm_load_print_meta: model params = 24.15 B
llm_load_print_meta: model size = 16.10 GiB (5.73 BPW)
llm_load_print_meta: general.name = .
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: PAD token = 1 '<s>'
llm_load_print_meta: LF token = 13 '<0x0A>'
time=2024-06-26T08:51:10.898+02:00 level=INFO source=server.go:594 msg="waiting for server to become available" status="llm server loading model"
/opt/amdgpu/share/libdrm/amdgpu.ids: No such file or directory
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, compute capability 10.3, VMM: no
llm_load_tensors: ggml ctx size = 0.54 MiB
time=2024-06-26T08:51:13.611+02:00 level=INFO source=server.go:594 msg="waiting for server to become available" status="llm server not responding"
llm_load_tensors: offloading 23 repeating layers to GPU
llm_load_tensors: offloaded 23/33 layers to GPU
llm_load_tensors: ROCm0 buffer size = 11593.03 MiB
llm_load_tensors: ROCm_Host buffer size = 4893.42 MiB
time=2024-06-26T08:51:13.863+02:00 level=INFO source=server.go:594 msg="waiting for server to become available" status="llm server loading model"
llama_new_context_with_model: n_ctx = 16384
llama_new_context_with_model: n_batch = 512
llama_new_context_with_model: n_ubatch = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: ROCm0 KV buffer size = 1472.00 MiB
llama_kv_cache_init: ROCm_Host KV buffer size = 576.00 MiB
llama_new_context_with_model: KV self size = 2048.00 MiB, K (f16): 1024.00 MiB, V (f16): 1024.00 MiB
llama_new_context_with_model: ROCm_Host output buffer size = 0.28 MiB
llama_new_context_with_model: ROCm0 compute buffer size = 1147.00 MiB
llama_new_context_with_model: ROCm_Host compute buffer size = 40.01 MiB
llama_new_context_with_model: graph nodes = 1510
llama_new_context_with_model: graph splits = 112
time=2024-06-26T08:51:46.061+02:00 level=INFO source=server.go:599 msg="llama runner started in 35.42 seconds"
CUDA error: out of memory
current device: 0, in function alloc at /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu:290
ggml_cuda_device_malloc(&ptr, look_ahead_size, device)
GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu:100: !"CUDA error"