MUSA error: operation not supported #26
Description
Name and Version
./llama-cli --version
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 8 MUSA devices:
Device 0: MTT S4000, compute capability 2.2, VMM: yes
Device 1: MTT S4000, compute capability 2.2, VMM: yes
Device 2: MTT S4000, compute capability 2.2, VMM: yes
Device 3: MTT S4000, compute capability 2.2, VMM: yes
Device 4: MTT S3000, compute capability 2.1, VMM: yes
Device 5: MTT S3000, compute capability 2.1, VMM: yes
Device 6: MTT S3000, compute capability 2.1, VMM: yes
Device 7: MTT S3000, compute capability 2.1, VMM: yes
version: 4749 (ggml-org/llama.cpp@ee02ad0)
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
Operating systems
Linux
GGML backends
Musa
Hardware
Hygon 7385x2 (32C x2)
Moorethreads: S4000 x8
RAM: 512GB
Models
DeepSeek-R1-Distill-Qwen-32B-Q4_K_M
Problem description & steps to reproduce
Command:
./llama-server -t 32 -c 8192 -fa -np 4 -m /root/DeepSeek-R1-Distill-Qwen-32B-GGUF/DeepSeek-R1-Distill-Qwen-32B-Q4_K_M.gguf -ngl 100 --no-warmup --port 100
86 --host 0.0.0.0 -v
First Bad Commit
No response
Relevant log output
3. Error log:
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 8 MUSA devices:
Device 0: MTT S4000, compute capability 2.2, VMM: yes
Device 1: MTT S4000, compute capability 2.2, VMM: yes
Device 2: MTT S4000, compute capability 2.2, VMM: yes
Device 3: MTT S4000, compute capability 2.2, VMM: yes
Device 4: MTT S3000, compute capability 2.1, VMM: yes
Device 5: MTT S3000, compute capability 2.1, VMM: yes
Device 6: MTT S3000, compute capability 2.1, VMM: yes
Device 7: MTT S3000, compute capability 2.1, VMM: yes
build: 4749 (ee02ad02) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
system info: n_threads = 32, n_threads_batch = 32, total_threads = 64
system_info: n_threads = 32 (n_threads_batch = 32) / 64 | MUSA : F16 = 1 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | FA_ALL_QUANTS = 1 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | OPENMP = 1 | AARCH64_REPACK = 1 |
main: HTTP server is listening, hostname: 0.0.0.0, port: 10086, http threads: 63
main: loading model
srv load_model: loading model '/root/DeepSeek-R1-Distill-Qwen-32B-GGUF/DeepSeek-R1-Distill-Qwen-32B-Q4_K_M.gguf'
llama_model_load_from_file_impl: using device MUSA0 (MTT S4000) - 49055 MiB free
llama_model_load_from_file_impl: using device MUSA1 (MTT S4000) - 49055 MiB free
llama_model_load_from_file_impl: using device MUSA2 (MTT S4000) - 49055 MiB free
llama_model_load_from_file_impl: using device MUSA3 (MTT S4000) - 49055 MiB free
llama_model_load_from_file_impl: using device MUSA4 (MTT S3000) - 32674 MiB free
llama_model_load_from_file_impl: using device MUSA5 (MTT S3000) - 32674 MiB free
llama_model_load_from_file_impl: using device MUSA6 (MTT S3000) - 32674 MiB free
llama_model_load_from_file_impl: using device MUSA7 (MTT S3000) - 32674 MiB free
llama_model_loader: loaded meta data with 27 key-value pairs and 771 tensors from /root/DeepSeek-R1-Distill-Qwen-32B-GGUF/DeepSeek-R1-Distill-Qwen-32B-Q4_K_M.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 32B
llama_model_loader: - kv 3: general.organization str = Deepseek Ai
llama_model_loader: - kv 4: general.basename str = DeepSeek-R1-Distill-Qwen
llama_model_loader: - kv 5: general.size_label str = 32B
llama_model_loader: - kv 6: qwen2.block_count u32 = 64
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 = 27648
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: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 15: tokenizer.ggml.pre str = deepseek-r1-qwen
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,152064] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 18: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 151646
llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 151643
llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 151654
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 = {% if not add_generation_prompt is de...
llama_model_loader: - kv 25: general.quantization_version u32 = 2
llama_model_loader: - kv 26: general.file_type u32 = 15
llama_model_loader: - type f32: 321 tensors
llama_model_loader: - type q4_K: 385 tensors
llama_model_loader: - type q6_K: 65 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 18.48 GiB (4.85 BPW)
init_tokenizer: initializing tokenizer for type 2
load: control token: 151660 '<|fim_middle|>' is not marked as EOG
load: control token: 151659 '<|fim_prefix|>' is not marked as EOG
load: control token: 151653 '<|vision_end|>' is not marked as EOG
load: control token: 151645 '<｜Assistant｜>' is not marked as EOG
load: control token: 151644 '<｜User｜>' is not marked as EOG
load: control token: 151655 '<|image_pad|>' is not marked as EOG
load: control token: 151651 '<|quad_end|>' is not marked as EOG
load: control token: 151646 '<｜begin▁of▁sentence｜>' is not marked as EOG
load: control token: 151643 '<｜end▁of▁sentence｜>' is not marked as EOG
load: control token: 151652 '<|vision_start|>' is not marked as EOG
load: control token: 151647 '<|EOT|>' is not marked as EOG
load: control token: 151654 '<|vision_pad|>' is not marked as EOG
load: control token: 151656 '<|video_pad|>' is not marked as EOG
load: control token: 151661 '<|fim_suffix|>' is not marked as EOG
load: control token: 151650 '<|quad_start|>' is not marked as EOG
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 = 64
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 = 27648
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 = 32B
print_info: model params = 32.76 B
print_info: general.name = DeepSeek R1 Distill Qwen 32B
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 = 151654 '<|vision_pad|>'
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: layer 0 assigned to device MUSA0
load_tensors: layer 1 assigned to device MUSA0
load_tensors: layer 2 assigned to device MUSA0
load_tensors: layer 3 assigned to device MUSA0
load_tensors: layer 4 assigned to device MUSA0
load_tensors: layer 5 assigned to device MUSA0
load_tensors: layer 6 assigned to device MUSA0
load_tensors: layer 7 assigned to device MUSA0
load_tensors: layer 8 assigned to device MUSA0
load_tensors: layer 9 assigned to device MUSA0
load_tensors: layer 10 assigned to device MUSA1
load_tensors: layer 11 assigned to device MUSA1
load_tensors: layer 12 assigned to device MUSA1
load_tensors: layer 13 assigned to device MUSA1
load_tensors: layer 14 assigned to device MUSA1
load_tensors: layer 15 assigned to device MUSA1
load_tensors: layer 16 assigned to device MUSA1
load_tensors: layer 17 assigned to device MUSA1
load_tensors: layer 18 assigned to device MUSA1
load_tensors: layer 19 assigned to device MUSA1
load_tensors: layer 20 assigned to device MUSA2
load_tensors: layer 21 assigned to device MUSA2
load_tensors: layer 22 assigned to device MUSA2
load_tensors: layer 23 assigned to device MUSA2
load_tensors: layer 24 assigned to device MUSA2
load_tensors: layer 25 assigned to device MUSA2
load_tensors: layer 26 assigned to device MUSA2
load_tensors: layer 27 assigned to device MUSA2
load_tensors: layer 28 assigned to device MUSA2
load_tensors: layer 29 assigned to device MUSA2
load_tensors: layer 30 assigned to device MUSA3
load_tensors: layer 31 assigned to device MUSA3
load_tensors: layer 32 assigned to device MUSA3
load_tensors: layer 33 assigned to device MUSA3
load_tensors: layer 34 assigned to device MUSA3
load_tensors: layer 35 assigned to device MUSA3
load_tensors: layer 36 assigned to device MUSA3
load_tensors: layer 37 assigned to device MUSA3
load_tensors: layer 38 assigned to device MUSA3
load_tensors: layer 39 assigned to device MUSA3
load_tensors: layer 40 assigned to device MUSA4
load_tensors: layer 41 assigned to device MUSA4
load_tensors: layer 42 assigned to device MUSA4
load_tensors: layer 43 assigned to device MUSA4
load_tensors: layer 44 assigned to device MUSA4
load_tensors: layer 45 assigned to device MUSA4
load_tensors: layer 46 assigned to device MUSA5
load_tensors: layer 47 assigned to device MUSA5
load_tensors: layer 48 assigned to device MUSA5
load_tensors: layer 49 assigned to device MUSA5
load_tensors: layer 50 assigned to device MUSA5
load_tensors: layer 51 assigned to device MUSA5
load_tensors: layer 52 assigned to device MUSA5
load_tensors: layer 53 assigned to device MUSA6
load_tensors: layer 54 assigned to device MUSA6
load_tensors: layer 55 assigned to device MUSA6
load_tensors: layer 56 assigned to device MUSA6
load_tensors: layer 57 assigned to device MUSA6
load_tensors: layer 58 assigned to device MUSA6
load_tensors: layer 59 assigned to device MUSA7
load_tensors: layer 60 assigned to device MUSA7
load_tensors: layer 61 assigned to device MUSA7
load_tensors: layer 62 assigned to device MUSA7
load_tensors: layer 63 assigned to device MUSA7
load_tensors: layer 64 assigned to device MUSA7
load_tensors: tensor 'token_embd.weight' (q4_K) (and 0 others) cannot be used with preferred buffer type CPU_AARCH64, using CPU instead
load_tensors: offloading 64 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 65/65 layers to GPU
load_tensors: MUSA0 model buffer size = 2905.04 MiB
load_tensors: MUSA1 model buffer size = 2760.66 MiB
load_tensors: MUSA2 model buffer size = 2724.57 MiB
load_tensors: MUSA3 model buffer size = 2724.57 MiB
load_tensors: MUSA4 model buffer size = 1641.96 MiB
load_tensors: MUSA5 model buffer size = 1939.68 MiB
load_tensors: MUSA6 model buffer size = 1714.15 MiB
load_tensors: MUSA7 model buffer size = 2097.71 MiB
load_tensors: CPU_Mapped model buffer size = 417.66 MiB
................................................................................................
llama_init_from_model: n_seq_max = 4
llama_init_from_model: n_ctx = 8192
llama_init_from_model: n_ctx_per_seq = 2048
llama_init_from_model: n_batch = 2048
llama_init_from_model: n_ubatch = 512
llama_init_from_model: flash_attn = 1
llama_init_from_model: freq_base = 1000000.0
llama_init_from_model: freq_scale = 1
llama_init_from_model: n_ctx_per_seq (2048) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 64, can_shift = 1
llama_kv_cache_init: layer 0: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 1: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 2: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 3: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 4: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 5: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 6: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 7: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 8: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 9: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 10: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 11: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 12: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 13: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 14: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 15: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 16: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 17: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 18: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 19: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 20: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 21: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 22: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 23: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 24: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 25: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 26: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 27: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 28: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 29: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 30: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 31: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 32: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 33: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 34: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 35: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 36: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 37: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 38: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 39: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 40: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 41: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 42: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 43: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 44: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 45: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 46: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 47: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 48: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 49: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 50: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 51: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 52: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 53: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 54: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 55: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 56: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 57: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 58: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 59: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 60: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 61: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 62: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 63: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: MUSA0 KV buffer size = 320.00 MiB
llama_kv_cache_init: MUSA1 KV buffer size = 320.00 MiB
llama_kv_cache_init: MUSA2 KV buffer size = 320.00 MiB
llama_kv_cache_init: MUSA3 KV buffer size = 320.00 MiB
llama_kv_cache_init: MUSA4 KV buffer size = 192.00 MiB
llama_kv_cache_init: MUSA5 KV buffer size = 224.00 MiB
llama_kv_cache_init: MUSA6 KV buffer size = 192.00 MiB
llama_kv_cache_init: MUSA7 KV buffer size = 160.00 MiB
llama_init_from_model: KV self size = 2048.00 MiB, K (f16): 1024.00 MiB, V (f16): 1024.00 MiB
llama_init_from_model: MUSA_Host output buffer size = 2.32 MiB
llama_init_from_model: pipeline parallelism enabled (n_copies=4)
llama_init_from_model: MUSA0 compute buffer size = 632.01 MiB
llama_init_from_model: MUSA1 compute buffer size = 568.01 MiB
llama_init_from_model: MUSA2 compute buffer size = 568.01 MiB
llama_init_from_model: MUSA3 compute buffer size = 568.01 MiB
llama_init_from_model: MUSA4 compute buffer size = 408.01 MiB
llama_init_from_model: MUSA5 compute buffer size = 448.01 MiB
llama_init_from_model: MUSA6 compute buffer size = 408.01 MiB
llama_init_from_model: MUSA7 compute buffer size = 547.02 MiB
llama_init_from_model: MUSA_Host compute buffer size = 10858.02 MiB
llama_init_from_model: graph nodes = 1991
llama_init_from_model: graph splits = 137
common_init_from_params: setting dry_penalty_last_n to ctx_size = 8192
srv init: initializing slots, n_slots = 4
slot init: id 0 | task -1 | new slot n_ctx_slot = 2048
slot reset: id 0 | task -1 |
slot init: id 1 | task -1 | new slot n_ctx_slot = 2048
slot reset: id 1 | task -1 |
slot init: id 2 | task -1 | new slot n_ctx_slot = 2048
slot reset: id 2 | task -1 |
slot init: id 3 | task -1 | new slot n_ctx_slot = 2048
slot reset: id 3 | task -1 |
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 '' in content %}{% set content = content.split('')[-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://0.0.0.0:10086 - starting the main loop
que start_loop: processing new tasks
que start_loop: update slots
srv update_slots: all slots are idle
srv kv_cache_cle: clearing KV cache
que start_loop: waiting for new tasks
request: {"messages":[{"role":"system","content":"\nCurrent model: gpt-4o\nCurrent date: 2025-02-26T02:45:26.215Z\n\nYou are a helpful assistant."},{"role":"user","content":"你好啊"},{"role":"user","content":"你好"}],"model":"gpt-4o","temperature":0.7,"top_p":0.9,"stream":true}
srv params_from_: Grammar:
srv params_from_: Grammar lazy: false
srv params_from_: Chat format: Content-only
srv add_waiting_: add task 0 to waiting list. current waiting = 0 (before add)
que post: new task, id = 0/1, front = 0
que start_loop: processing new tasks
que start_loop: processing task, id = 0
slot get_availabl: id 0 | task -1 | selected slot by lru, t_last = -1
slot reset: id 0 | task -1 |
slot launch_slot_: id 0 | task 0 | launching slot : {"id":0,"id_task":0,"n_ctx":2048,"speculative":false,"is_processing":false,"non_causal":false,"params":{"n_predict":-1,"seed":4294967295,"temperature":0.699999988079071,"dynatemp_range":0.0,"dynatemp_exponent":1.0,"top_k":40,"top_p":0.8999999761581421,"min_p":0.05000000074505806,"xtc_probability":0.0,"xtc_threshold":0.10000000149011612,"typical_p":1.0,"repeat_last_n":64,"repeat_penalty":1.0,"presence_penalty":0.0,"frequency_penalty":0.0,"dry_multiplier":0.0,"dry_base":1.75,"dry_allowed_length":2,"dry_penalty_last_n":8192,"dry_sequence_breakers":["\n",":",""","*"],"mirostat":0,"mirostat_tau":5.0,"mirostat_eta":0.10000000149011612,"stop":[],"max_tokens":-1,"n_keep":0,"n_discard":0,"ignore_eos":false,"stream":true,"logit_bias":[],"n_probs":0,"min_keep":0,"grammar":"","grammar_trigger_words":[],"grammar_trigger_tokens":[],"preserved_tokens":[],"chat_format":"Content-only","samplers":["penalties","dry","top_k","typ_p","top_p","min_p","xtc","temperature"],"speculative.n_max":16,"speculative.n_min":0,"speculative.p_min":0.75,"timings_per_token":false,"post_sampling_probs":false,"lora":[]},"prompt":"<｜begin▁of▁sentence｜>\nCurrent model: gpt-4o\nCurrent date: 2025-02-26T02:45:26.215Z\n\nYou are a helpful assistant.\n\n<｜User｜>你好啊<｜User｜>你好<｜Assistant｜>","next_token":{"has_next_token":true,"has_new_line":false,"n_remain":-1,"n_decoded":0,"stopping_word":""}}
slot launch_slot_: id 0 | task 0 | processing task
que start_loop: update slots
srv update_slots: posting NEXT_RESPONSE
que post: new task, id = 1, front = 0
slot update_slots: id 0 | task 0 | new prompt, n_ctx_slot = 2048, n_keep = 0, n_prompt_tokens = 52
slot update_slots: id 0 | task 0 | prompt token 0: 151646 '<｜begin▁of▁sentence｜>'
slot update_slots: id 0 | task 0 | prompt token 1: 198 '
'
slot update_slots: id 0 | task 0 | prompt token 2: 5405 'Current'
slot update_slots: id 0 | task 0 | prompt token 3: 1614 ' model'
slot update_slots: id 0 | task 0 | prompt token 4: 25 ':'
slot update_slots: id 0 | task 0 | prompt token 5: 342 ' g'
slot update_slots: id 0 | task 0 | prompt token 6: 417 'pt'
slot update_slots: id 0 | task 0 | prompt token 7: 12 '-'
slot update_slots: id 0 | task 0 | prompt token 8: 19 '4'
slot update_slots: id 0 | task 0 | prompt token 9: 78 'o'
slot update_slots: id 0 | task 0 | prompt token 10: 198 '
'
slot update_slots: id 0 | task 0 | prompt token 11: 5405 'Current'
slot update_slots: id 0 | task 0 | prompt token 12: 2400 ' date'
slot update_slots: id 0 | task 0 | prompt token 13: 25 ':'
slot update_slots: id 0 | task 0 | prompt token 14: 220 ' '
slot update_slots: id 0 | task 0 | prompt token 15: 17 '2'
slot update_slots: id 0 | task 0 | kv cache rm [0, end)
slot update_slots: id 0 | task 0 | prompt processing progress, n_past = 52, n_tokens = 52, progress = 1.000000
slot update_slots: id 0 | task 0 | prompt done, n_past = 52, n_tokens = 52
srv update_slots: decoding batch, n_tokens = 52
/root/musa/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:73: MUSA error
MUSA error: operation not supported
current device: 0, in function alloc at /root/musa/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:443
muMemAddressReserve(&pool_addr, CUDA_POOL_VMM_MAX_SIZE, 0, 0, 0)
request: {"messages":[{"role":"user","content":"Based on the chat history, give this conversation a name.\nKeep it short - 10 characters max, no quotes.\nUse 简体中文.\nJust provide the name, nothing else.\n\nHere's the conversation:\n\n\n你好啊\n\n---------\n\n\n\n---------\n\n你好\n\n---------\n\n...\n\n\nName this conversation in 10 characters or less.\nUse 简体中文.\nOnly give the name, nothing else.\n\nThe name is:"}],"model":"gpt-4o","temperature":0.7,"top_p":0.9,"stream":true}
srv params_from_: Grammar:
srv params_from_: Grammar lazy: false
srv params_from_: Chat format: Content-only
srv add_waiting_: add task 2 to waiting list. current waiting = 1 (before add)
que post: new task, id = 2/1, front = 0