Closed
Description
Name and Version
b4742
Operating systems
Linux
GGML backends
HIP, CPU
Hardware
Atlas 300I Duo
Software Version : 24.1.rc2
Firmware Version : 7.3.0.1.231
toolkit : 8.0.0
Models
DeepSeek-R1-Distill-Qwen-14B_F16.gguf
Problem description & steps to reproduce
./llama-server -m /DeepSeek-R1-Distill-Qwen-14B.gguf -e -ngl 33 -sm layer
i hava tried --main-gpu ，but problem still persists.
Output garbled in dual-GPU environment
First Bad Commit
No response
Relevant log output
bash-5.2# ./llama-server -m ../../../DeepSeek-R1-Distill-Qwen-14B.gguf -e -ngl 33 -sm layer
build: 0 (unknown) with cc (NGTOS-2.6.2210) 9.5.0 for aarch64-native_tos-linux-gnu
system info: n_threads = 96, n_threads_batch = 96, total_threads = 96
system_info: n_threads = 96 (n_threads_batch = 96) / 96 | CPU : NEON = 1 | ARM_FMA = 1 | FP16_VA = 1 | DOTPROD = 1 | LLAMAFILE = 1 | OPENMP = 1 | AARCH64_REPACK = 1 |
main: HTTP server is listening, hostname: 127.0.0.1, port: 8080, http threads: 95
main: loading model
srv load_model: loading model '../../../DeepSeek-R1-Distill-Qwen-14B.gguf'
llama_model_load_from_file_impl: using device CANN0 (Ascend310P3) - 20650 MiB free
llama_model_load_from_file_impl: using device CANN1 (Ascend310P3) - 20111 MiB free
llama_model_load_from_file_impl: using device CANN2 (Ascend310P3) - 20439 MiB free
llama_model_load_from_file_impl: using device CANN3 (Ascend310P3) - 20318 MiB free
llama_model_loader: loaded meta data with 27 key-value pairs and 579 tensors from ../../../DeepSeek-R1-Distill-Qwen-14B.gguf (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 = qwen2
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = DeepSeek R1 Distill Qwen 14B
llama_model_loader: - kv 3: general.basename str = DeepSeek-R1-Distill-Qwen
llama_model_loader: - kv 4: general.size_label str = 14B
llama_model_loader: - kv 5: general.license str = mit
llama_model_loader: - kv 6: qwen2.block_count u32 = 48
llama_model_loader: - kv 7: qwen2.context_length u32 = 131072
llama_model_loader: - kv 8: qwen2.embedding_length u32 = 5120
llama_model_loader: - kv 9: qwen2.feed_forward_length u32 = 13824
llama_model_loader: - kv 10: qwen2.attention.head_count u32 = 40
llama_model_loader: - kv 11: qwen2.attention.head_count_kv u32 = 8
llama_model_loader: - kv 12: qwen2.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 13: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 14: general.file_type u32 = 1
llama_model_loader: - kv 15: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 16: tokenizer.ggml.pre str = deepseek-r1-qwen
llama_model_loader: - kv 17: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 19: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 20: tokenizer.ggml.bos_token_id u32 = 151646
llama_model_loader: - kv 21: tokenizer.ggml.eos_token_id u32 = 151643
llama_model_loader: - kv 22: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 23: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 24: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 25: tokenizer.chat_template str = {% if not add_generation_prompt is de...
llama_model_loader: - kv 26: general.quantization_version u32 = 2
llama_model_loader: - type f32: 241 tensors
llama_model_loader: - type f16: 338 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = F16
print_info: file size = 27.51 GiB (16.00 BPW)
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 22
load: token to piece cache size = 0.9310 MB
print_info: arch = qwen2
print_info: vocab_only = 0
print_info: n_ctx_train = 131072
print_info: n_embd = 5120
print_info: n_layer = 48
print_info: n_head = 40
print_info: n_head_kv = 8
print_info: n_rot = 128
print_info: n_swa = 0
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 5
print_info: n_embd_k_gqa = 1024
print_info: n_embd_v_gqa = 1024
print_info: f_norm_eps = 0.0e+00
print_info: f_norm_rms_eps = 1.0e-05
print_info: f_clamp_kqv = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale = 0.0e+00
print_info: n_ff = 13824
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = 2
print_info: rope scaling = linear
print_info: freq_base_train = 1000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 131072
print_info: rope_finetuned = unknown
print_info: ssm_d_conv = 0
print_info: ssm_d_inner = 0
print_info: ssm_d_state = 0
print_info: ssm_dt_rank = 0
print_info: ssm_dt_b_c_rms = 0
print_info: model type = 14B
print_info: model params = 14.77 B
print_info: general.name = DeepSeek R1 Distill Qwen 14B
print_info: vocab type = BPE
print_info: n_vocab = 152064
print_info: n_merges = 151387
print_info: BOS token = 151646 '<｜begin▁of▁sentence｜>'
print_info: EOS token = 151643 '<｜end▁of▁sentence｜>'
print_info: EOT token = 151643 '<｜end▁of▁sentence｜>'
print_info: PAD token = 151643 '<｜end▁of▁sentence｜>'
print_info: LF token = 198 'Ċ'
print_info: FIM PRE token = 151659 '<|fim_prefix|>'
print_info: FIM SUF token = 151661 '<|fim_suffix|>'
print_info: FIM MID token = 151660 '<|fim_middle|>'
print_info: FIM PAD token = 151662 '<|fim_pad|>'
print_info: FIM REP token = 151663 '<|repo_name|>'
print_info: FIM SEP token = 151664 '<|file_sep|>'
print_info: EOG token = 151643 '<｜end▁of▁sentence｜>'
print_info: EOG token = 151662 '<|fim_pad|>'
print_info: EOG token = 151663 '<|repo_name|>'
print_info: EOG token = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 33 repeating layers to GPU
load_tensors: offloaded 33/49 layers to GPU
load_tensors: CPU_Mapped model buffer size = 28173.21 MiB
load_tensors: CANN0 model buffer size = 4725.60 MiB
load_tensors: CANN1 model buffer size = 4200.53 MiB
load_tensors: CANN2 model buffer size = 4200.53 MiB
load_tensors: CANN3 model buffer size = 4200.53 MiB
............................................................................................
llama_init_from_model: n_seq_max = 1
llama_init_from_model: n_ctx = 4096
llama_init_from_model: n_ctx_per_seq = 4096
llama_init_from_model: n_batch = 2048
llama_init_from_model: n_ubatch = 512
llama_init_from_model: flash_attn = 0
llama_init_from_model: freq_base = 1000000.0
llama_init_from_model: freq_scale = 1
llama_init_from_model: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 4096, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 48, can_shift = 1
llama_kv_cache_init: CPU KV buffer size = 240.00 MiB
llama_kv_cache_init: CANN0 KV buffer size = 144.00 MiB
llama_kv_cache_init: CANN1 KV buffer size = 128.00 MiB
llama_kv_cache_init: CANN2 KV buffer size = 128.00 MiB
llama_kv_cache_init: CANN3 KV buffer size = 128.00 MiB
llama_init_from_model: KV self size = 768.00 MiB, K (f16): 384.00 MiB, V (f16): 384.00 MiB
llama_init_from_model: CPU output buffer size = 0.58 MiB
llama_init_from_model: CANN0 compute buffer size = 1792.00 MiB
llama_init_from_model: CANN1 compute buffer size = 368.00 MiB
llama_init_from_model: CANN2 compute buffer size = 368.00 MiB
llama_init_from_model: CANN3 compute buffer size = 368.00 MiB
llama_init_from_model: CANN_Host compute buffer size = 18.01 MiB
llama_init_from_model: graph nodes = 1686
llama_init_from_model: graph splits = 217 (with bs=512), 6 (with bs=1)
common_init_from_params: setting dry_penalty_last_n to ctx_size = 4096
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
srv init: initializing slots, n_slots = 1
slot init: id 0 | task -1 | new slot n_ctx_slot = 4096
main: model loaded
main: chat template, chat_template: {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '' + '\n' + tool['function']['arguments'] + '\n' + '' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '' + '\n' + tool['function']['arguments'] + '\n' + '' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}, example_format: 'You are a helpful assistant
<｜User｜>Hello<｜Assistant｜>Hi there<｜end▁of▁sentence｜><｜User｜>How are you?<｜Assistant｜>'
main: server is listening on http://127.0.0.1:8080 - starting the main loop
srv update_slots: all slots are idle
srv params_from_: Chat format: Content-only
slot launch_slot_: id 0 | task 0 | processing task
slot update_slots: id 0 | task 0 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 10
slot update_slots: id 0 | task 0 | kv cache rm [0, end)
slot update_slots: id 0 | task 0 | prompt processing progress, n_past = 10, n_tokens = 10, progress = 1.000000
slot update_slots: id 0 | task 0 | prompt done, n_past = 10, n_tokens = 10