Open
Description
Name and Version
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 3080 Laptop GPU, compute capability 8.6, VMM: yes
version: 0 (unknown)
built with gcc (Ubuntu 11.2.0-19ubuntu1) 11.2.0 for x86_64-linux-gn
Operating systems
Linux
GGML backends
CUDA
Hardware
NVIDIA GeForce RTX 3080 Laptop GPU
Models
No response
Problem description & steps to reproduce
when i run llama-cli infer qwen3 with , when infer 2th/3th/... round，Unable to obtain complete output。
First Bad Commit
No response
Relevant log output
./llama-cli -m '/home/qxy/Desktop/Qwen3-752M-0___6B-F16.gguf'
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 3080 Laptop GPU, compute capability 8.6, VMM: yes
build: 0 (unknown) with gcc (Ubuntu 11.2.0-19ubuntu1) 11.2.0 for x86_64-linux-gnu
main: llama backend init
main: load the model and apply lora adapter, if any
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3080 Laptop GPU) - 13784 MiB free
llama_model_loader: loaded meta data with 35 key-value pairs and 311 tensors from /home/qxy/Desktop/Qwen3-752M-0___6B-F16.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 = qwen3
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Qwen3 0___6B
llama_model_loader: - kv 3: general.finetune str = 0___6B
llama_model_loader: - kv 4: general.basename str = Qwen3
llama_model_loader: - kv 5: general.size_label str = 752M
llama_model_loader: - kv 6: general.license str = apache-2.0
llama_model_loader: - kv 7: general.license.link str = https://huggingface.co/Qwen/Qwen3-0.6...
llama_model_loader: - kv 8: general.base_model.count u32 = 1
llama_model_loader: - kv 9: general.base_model.0.name str = Qwen3 0.6B Base
llama_model_loader: - kv 10: general.base_model.0.organization str = Qwen
llama_model_loader: - kv 11: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen3-0.6...
llama_model_loader: - kv 12: general.tags arr[str,1] = ["text-generation"]
llama_model_loader: - kv 13: qwen3.block_count u32 = 28
llama_model_loader: - kv 14: qwen3.context_length u32 = 40960
llama_model_loader: - kv 15: qwen3.embedding_length u32 = 1024
llama_model_loader: - kv 16: qwen3.feed_forward_length u32 = 3072
llama_model_loader: - kv 17: qwen3.attention.head_count u32 = 16
llama_model_loader: - kv 18: qwen3.attention.head_count_kv u32 = 8
llama_model_loader: - kv 19: qwen3.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 20: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 21: qwen3.attention.key_length u32 = 128
llama_model_loader: - kv 22: qwen3.attention.value_length u32 = 128
llama_model_loader: - kv 23: general.file_type u32 = 1
llama_model_loader: - kv 24: general.quantization_version u32 = 2
llama_model_loader: - kv 25: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 26: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 27: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 28: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 29: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 30: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 31: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 32: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 33: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 34: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
llama_model_loader: - type f32: 113 tensors
llama_model_loader: - type f16: 198 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = F16
print_info: file size = 1.40 GiB (16.00 BPW)
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch = qwen3
print_info: vocab_only = 0
print_info: n_ctx_train = 40960
print_info: n_embd = 1024
print_info: n_layer = 28
print_info: n_head = 16
print_info: n_head_kv = 8
print_info: n_rot = 128
print_info: n_swa = 0
print_info: is_swa_any = 0
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 2
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-06
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: f_attn_scale = 0.0e+00
print_info: n_ff = 3072
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 = 40960
print_info: rope_finetuned = unknown
print_info: model type = 0.6B
print_info: model params = 751.63 M
print_info: general.name = Qwen3 0___6B
print_info: vocab type = BPE
print_info: n_vocab = 151936
print_info: n_merges = 151387
print_info: BOS token = 151643 '<|endoftext|>'
print_info: EOS token = 151645 '<|im_end|>'
print_info: EOT token = 151645 '<|im_end|>'
print_info: PAD token = 151643 '<|endoftext|>'
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 '<|endoftext|>'
print_info: EOG token = 151645 '<|im_end|>'
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 0 repeating layers to GPU
load_tensors: offloaded 0/29 layers to GPU
load_tensors: CPU_Mapped model buffer size = 1433.75 MiB
.............................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 1
llama_context: n_ctx = 4096
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch = 2048
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = 0
llama_context: freq_base = 1000000.0
llama_context: freq_scale = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
llama_context: CPU output buffer size = 0.58 MiB
llama_kv_cache_unified: CPU KV buffer size = 448.00 MiB
llama_kv_cache_unified: size = 448.00 MiB ( 4096 cells, 28 layers, 1 seqs), K (f16): 224.00 MiB, V (f16): 224.00 MiB
llama_kv_cache_unified: LLAMA_SET_ROWS=0, using old ggml_cpy() method for backwards compatibility
llama_context: CUDA0 compute buffer size = 601.50 MiB
llama_context: CUDA_Host compute buffer size = 12.01 MiB
llama_context: graph nodes = 1126
llama_context: graph splits = 368 (with bs=512), 1 (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)
main: llama threadpool init, n_threads = 8
main: chat template is available, enabling conversation mode (disable it with -no-cnv)
main: chat template example:
<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
Hello<|im_end|>
<|im_start|>assistant
Hi there<|im_end|>
<|im_start|>user
How are you?<|im_end|>
<|im_start|>assistant
system_info: n_threads = 8 (n_threads_batch = 8) / 16 | CUDA : ARCHS = 500,610,700,750,800,860,890 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 |
main: interactive mode on.
sampler seed: 4269913888
sampler params:
repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000
dry_multiplier = 0.000, dry_base = 1.750, dry_allowed_length = 2, dry_penalty_last_n = 4096
top_k = 40, top_p = 0.950, min_p = 0.050, xtc_probability = 0.000, xtc_threshold = 0.100, typical_p = 1.000, top_n_sigma = -1.000, temp = 0.800
mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
generate: n_ctx = 4096, n_batch = 2048, n_predict = -1, n_keep = 0
== Running in interactive mode. ==
- Press Ctrl+C to interject at any time.
- Press Return to return control to the AI.
- To return control without starting a new line, end your input with '/'.
- If you want to submit another line, end your input with '\'.
- Not using system message. To change it, set a different value via -sys PROMPT
> 你好
<think>
好的，用户发来“你好”，我需要保持礼貌和友好。首先，确认用户是否想进行某种交流，比如问候或询问。然后，我应该用自然的中文回应，避免使用技术术语，让对话更轻松。同时，要确保回应符合中国的语言习惯，避免不自然的表达。最后，询问用户是否需要帮助，以促进进一步的互动。
</think>
你好！有什么可以帮助你的吗？需要聊天或讨论什么内容？
> 杭州天气
<think>
好的，用户现在问的是杭州的天气情况。我需要先确认用户的需求是什么。可能是想了解当前杭州的天气，或者计划去杭州旅游，想知道天气如何。在回答时，应该保持友好和专业的态度，同时提供有用的信息。首先，我应该确认天气的具体情况，比如温度、风速和天气状况。然后，考虑到用户可能需要帮助，可以询问是否需要进一步的信息或建议。另外，要注意用词自然，避免使用过于正式或复杂的句子，让用户感到舒适。最后，确保回应简洁明了，信息准确，同时保持开放式的提问，让用户有进一步交流的意愿。
> 上海呢
<think>
好的，用户之前询问了杭州的天气，现在转向上海。我需要先确认用户当前的需求。可能是想了解上海的天气，或者计划前往上海，想知道天气如何。在回答时，应该保持礼貌和友好，同时提供有用的信息。首先，我需要确认上海当前的天气情况，比如温度、风速和天气状况。然后，考虑到用户可能需要帮助，可以询问是否需要进一步的信息或建议。此外，要使用自然的中文表达，避免使用技术术语，让对话更顺畅。最后，确保回应简洁明了，信息准确，同时保持开放式的提问，让用户有进一步交流的意愿。
>