Cuda + Docker is generating only infinite text.

[Wandering-Magi]

OS: Arch Linux

+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 570.124.04             Driver Version: 570.124.04     CUDA Version: 12.8     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA GeForce RTX 3060 ...    Off |   00000000:01:00.0  On |                  N/A |
| N/A   38C    P8             14W /   80W |     814MiB /   6144MiB |      6%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

Build: Docker + llama.cpp:full-cuda
Built from this guide.

I just started messing around with AI this week, so forgive me for not already knowing all of the words.
I got the basic build working the other night, and got it running with llama-cli. The generation speed was pretty slow, so I wanted to use graphic acceleration so I can get some real speed. But is was working, so I know it's possible.
As usual, Nvidia on Arch continues to be the bane of my existence, but that's neither here nor there. I set up CUDA, installed the toolkit, installed docker, got everything configured and working. A fun learning experience.
If I run it using the example text, it generates text about making a website. Cool, works. The catch is getting the damn thing to pause for user input. Which the example won't do, but a few extra commands should change that.
This is the current command I'm using. All I'm trying to do right now is to get it into conversation mode.

docker run \
         --gpus all \
         -v /home/magi/Documents/Programming/AI/LLM/llama.cpp/models:/models \
         local/llama.cpp:full-cuda \
         --run \
         -m /models/Mistral-Nemo-Instruct-2407-Q6_K_L.gguf \
         -p "You are a helpful assistant awaiting your next instruction. Your answers will be clear and concise." \
         -cnv --chat-template chatml \
         -n 512 \
         --n-gpu-layers 1

For the record, I have tried both -p and -sys, just to see if it would help at all. Same problem.

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 3060 Laptop GPU, compute capability 8.6, VMM: yes
build: 4862 (be421fc4) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 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 3060 Laptop GPU) - 4858 MiB free
llama_model_loader: loaded meta data with 44 key-value pairs and 363 tensors from /models/Mistral-Nemo-Instruct-2407-Q6_K_L.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              = llama
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Mistral Nemo Instruct 2407
llama_model_loader: - kv   3:                            general.version str              = 2407
llama_model_loader: - kv   4:                           general.finetune str              = Instruct
llama_model_loader: - kv   5:                           general.basename str              = Mistral-Nemo
llama_model_loader: - kv   6:                         general.size_label str              = 12B
llama_model_loader: - kv   7:                            general.license str              = apache-2.0
llama_model_loader: - kv   8:                   general.base_model.count u32              = 1
llama_model_loader: - kv   9:                  general.base_model.0.name str              = Mistral Nemo Base 2407
llama_model_loader: - kv  10:               general.base_model.0.version str              = 2407
llama_model_loader: - kv  11:          general.base_model.0.organization str              = Mistralai
llama_model_loader: - kv  12:              general.base_model.0.repo_url str              = https://huggingface.co/mistralai/Mist...
llama_model_loader: - kv  13:                          general.languages arr[str,9]       = ["en", "fr", "de", "es", "it", "pt", ...
llama_model_loader: - kv  14:                          llama.block_count u32              = 40
llama_model_loader: - kv  15:                       llama.context_length u32              = 1024000
llama_model_loader: - kv  16:                     llama.embedding_length u32              = 5120
llama_model_loader: - kv  17:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv  18:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv  19:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv  20:                       llama.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  21:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  22:                 llama.attention.key_length u32              = 128
llama_model_loader: - kv  23:               llama.attention.value_length u32              = 128
llama_model_loader: - kv  24:                          general.file_type u32              = 18
llama_model_loader: - kv  25:                           llama.vocab_size u32              = 131072
llama_model_loader: - kv  26:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  27:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  28:                         tokenizer.ggml.pre str              = tekken
llama_model_loader: - kv  29:                      tokenizer.ggml.tokens arr[str,131072]  = ["<unk>", "<s>", "</s>", "[INST]", "[...
llama_model_loader: - kv  30:                  tokenizer.ggml.token_type arr[i32,131072]  = [3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, ...
llama_model_loader: - kv  31:                      tokenizer.ggml.merges arr[str,269443]  = ["Ġ Ġ", "Ġ t", "e r", "i n", "Ġ �..
llama_model_loader: - kv  32:                tokenizer.ggml.bos_token_id u32              = 1
llama_model_loader: - kv  33:                tokenizer.ggml.eos_token_id u32              = 2
llama_model_loader: - kv  34:            tokenizer.ggml.unknown_token_id u32              = 0
llama_model_loader: - kv  35:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  36:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  37:                    tokenizer.chat_template str              = {%- if messages[0]["role"] == "system...
llama_model_loader: - kv  38:            tokenizer.ggml.add_space_prefix bool             = false
llama_model_loader: - kv  39:               general.quantization_version u32              = 2
llama_model_loader: - kv  40:                      quantize.imatrix.file str              = /models_out/Mistral-Nemo-Instruct-240...
llama_model_loader: - kv  41:                   quantize.imatrix.dataset str              = /training_dir/calibration_datav3.txt
llama_model_loader: - kv  42:             quantize.imatrix.entries_count i32              = 280
llama_model_loader: - kv  43:              quantize.imatrix.chunks_count i32              = 128
llama_model_loader: - type  f32:   81 tensors
llama_model_loader: - type q8_0:    2 tensors
llama_model_loader: - type q6_K:  280 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q6_K
print_info: file size   = 9.66 GiB (6.78 BPW)
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 1000
load: token to piece cache size = 0.8498 MB
print_info: arch             = llama
print_info: vocab_only       = 0
print_info: n_ctx_train      = 1024000
print_info: n_embd           = 5120
print_info: n_layer          = 40
print_info: n_head           = 32
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            = 4
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             = 14336
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        = 0
print_info: rope scaling     = linear
print_info: freq_base_train  = 1000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 1024000
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       = 13B
print_info: model params     = 12.25 B
print_info: general.name     = Mistral Nemo Instruct 2407
print_info: vocab type       = BPE
print_info: n_vocab          = 131072
print_info: n_merges         = 269443
print_info: BOS token        = 1 '<s>'
print_info: EOS token        = 2 '</s>'
print_info: UNK token        = 0 '<unk>'
print_info: LF token         = 1010 'Ċ'
print_info: EOG token        = 2 '</s>'
print_info: max token length = 150
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 1 repeating layers to GPU
load_tensors: offloaded 1/41 layers to GPU
load_tensors:        CUDA0 model buffer size =   213.32 MiB
load_tensors:   CPU_Mapped model buffer size =  9679.51 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 (1024000) -- 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 = 40, can_shift = 1
llama_kv_cache_init:      CUDA0 KV buffer size =    16.00 MiB
llama_kv_cache_init:        CPU KV buffer size =   624.00 MiB
llama_init_from_model: KV self size  =  640.00 MiB, K (f16):  320.00 MiB, V (f16):  320.00 MiB
llama_init_from_model:        CPU  output buffer size =     0.50 MiB
llama_init_from_model:      CUDA0 compute buffer size =   946.00 MiB
llama_init_from_model:  CUDA_Host compute buffer size =    18.01 MiB
llama_init_from_model: graph nodes  = 1286
llama_init_from_model: graph splits = 433 (with bs=512), 3 (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)
*** User-specified prompt will pre-start conversation, did you mean to set --system-prompt (-sys) instead?
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 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | AARCH64_REPACK = 1 |

main: interactive mode on.
sampler seed: 1209183462
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-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
generate: n_ctx = 4096, n_batch = 2048, n_predict = 512, n_keep = 1

== 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

<|im_start|>user
You are a helpful assistant awaiting your next instruction. Your answers will be clear and concise.<|im_end|>
<|im_start|>assistant
Understood. Please proceed with your instructions.<|im_end|>

> <|im_start|>user
What is 27 times 34?<|im_end|>
<|im_start|>assistant
The product of 27 and 34 is 918.<|im_end|>

> <^C|
> im^C
> _start|^C
got 3 SIGTERM/SIGINTs, forcefully exiting

You can see at the end there, I'm using ctrl+c to interject, but it just won't stop. I have tried this at various lengths into the generation. After 3 calls it interrupts, and I go and use kill N to shut it down.

If I try to run it in --server --port 8080 mode, I can't access the server from my browser at http://127.0.0.1:8080. I have also tried --host 0.0.0.0 as I have found on other threads, but that doesn't work either.

docker run \
         --gpus all \
         -v /home/magi/Documents/Programming/AI/LLM/llama.cpp/models:/models \
         local/llama.cpp:full-cuda \
         --server \
         --port 8080 \
         -m /models/Mistral-Nemo-Instruct-2407-Q6_K_L.gguf \
         --chat-template gemma \
         -n 100 \
         --n-gpu-layers 1

In short, I'm at the end of my ability to figure my way through this. I feel like I'm one step away from figuring this out, but I'm facing a niche case of a new and rapidly developing field.