Eval bug: llama-server crash after 2 messages following commit 9070365

[firefox42]

Name and Version

./build/bin/llama-cli --version
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Instinct MI100, gfx908:sramecc+:xnack- (0x908), VMM: no, Wave Size: 64
Device 1: AMD Instinct MI100, gfx908:sramecc+:xnack- (0x908), VMM: no, Wave Size: 64
version: 5287 (9070365)
built with cc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 for x86_64-linux-gnu

Operating systems

Linux

GGML backends

HIP

Hardware

AMD Ryzen 7 5700X + 2x AMD Instinct MI100

Models

Qwen3-30B-A3B-Q8_0.gguf from https://huggingface.co/unsloth/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-Q8_0.gguf

Problem description & steps to reproduce

I compile llama.cpp for ROCm using HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" cmake -S . -B build -DGGML_HIP=ON -DAMDGPU_TARGETS=gfx908 -DCMAKE_BUILD_TYPE=Release -DGGML_HIP_ROCWMMA_FATTN=ON && cmake --build build --config Release -- -j 8

Then, I load Qwen3-30B-A3B-Q8_0.gguf using ./build/bin/llama-server -m models/gguf/Qwen3-30B-A3B-Q8_0.gguf -a Qwen3-30B-A3B-Q8_0.gguf -ngl 100 -sm layer -b 4096 -c 16384 --host [IP] --port [port] --api-key [key]

Next, I send a message the llama-server via the OpenAI API, specifically through Open-Webui. The first message seems to generate a response as expected.

Finally, I send a second message that continues the conversation, and it crashes llama-server.

Using the built-in webui lets me send 2 messages before the 3rd one exhibits the same behavior. Commit a7366fa did not resolve this issue.

First Bad Commit

9070365

Relevant log output

./build/bin/llama-server -m models/gguf/Qwen3-30B-A3B-Q8_0.gguf -a Qwen3-30B-A3B-Q8_0.gguf -ngl 100 -sm layer -b 4096 -c 16384 --host [ip] --port [port] --api-key [key]
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
  Device 0: AMD Instinct MI100, gfx908:sramecc+:xnack- (0x908), VMM: no, Wave Size: 64
  Device 1: AMD Instinct MI100, gfx908:sramecc+:xnack- (0x908), VMM: no, Wave Size: 64
build: 5287 (90703650) with cc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 for x86_64-linux-gnu
system info: n_threads = 8, n_threads_batch = 8, total_threads = 8

system_info: n_threads = 8 (n_threads_batch = 8) / 8 | ROCm : NO_VMM = 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: binding port with default address family
main: HTTP server is listening, hostname: [ip], port: [port], http threads: 7
main: loading model
srv    load_model: loading model 'models/gguf/Qwen3-30B-A3B-Q8_0.gguf'
llama_model_load_from_file_impl: using device ROCm0 (AMD Instinct MI100) - 32732 MiB free
llama_model_load_from_file_impl: using device ROCm1 (AMD Instinct MI100) - 32732 MiB free
llama_model_loader: loaded meta data with 35 key-value pairs and 579 tensors from models/gguf/Qwen3-30B-A3B-Q8_0.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              = qwen3moe
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen3-30B-A3B
llama_model_loader: - kv   3:                           general.basename str              = Qwen3-30B-A3B
llama_model_loader: - kv   4:                       general.quantized_by str              = Unsloth
llama_model_loader: - kv   5:                         general.size_label str              = 30B-A3B
llama_model_loader: - kv   6:                           general.repo_url str              = https://huggingface.co/unsloth
llama_model_loader: - kv   7:                       qwen3moe.block_count u32              = 48
llama_model_loader: - kv   8:                    qwen3moe.context_length u32              = 40960
llama_model_loader: - kv   9:                  qwen3moe.embedding_length u32              = 2048
llama_model_loader: - kv  10:               qwen3moe.feed_forward_length u32              = 6144
llama_model_loader: - kv  11:              qwen3moe.attention.head_count u32              = 32
llama_model_loader: - kv  12:           qwen3moe.attention.head_count_kv u32              = 4
llama_model_loader: - kv  13:                    qwen3moe.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  14:  qwen3moe.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  15:                 qwen3moe.expert_used_count u32              = 8
llama_model_loader: - kv  16:              qwen3moe.attention.key_length u32              = 128
llama_model_loader: - kv  17:            qwen3moe.attention.value_length u32              = 128
llama_model_loader: - kv  18:                      qwen3moe.expert_count u32              = 128
llama_model_loader: - kv  19:        qwen3moe.expert_feed_forward_length u32              = 768
llama_model_loader: - kv  20:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  21:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  22:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  23:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  24:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  25:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  26:            tokenizer.ggml.padding_token_id u32              = 151654
llama_model_loader: - kv  27:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  29:               general.quantization_version u32              = 2
llama_model_loader: - kv  30:                          general.file_type u32              = 7
llama_model_loader: - kv  31:                      quantize.imatrix.file str              = Qwen3-30B-A3B-GGUF/imatrix_unsloth.dat
llama_model_loader: - kv  32:                   quantize.imatrix.dataset str              = unsloth_calibration_Qwen3-30B-A3B.txt
llama_model_loader: - kv  33:             quantize.imatrix.entries_count i32              = 384
llama_model_loader: - kv  34:              quantize.imatrix.chunks_count i32              = 32
llama_model_loader: - type  f32:  241 tensors
llama_model_loader: - type q8_0:  338 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q8_0
print_info: file size   = 30.25 GiB (8.51 BPW) 
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch             = qwen3moe
print_info: vocab_only       = 0
print_info: n_ctx_train      = 40960
print_info: n_embd           = 2048
print_info: n_layer          = 48
print_info: n_head           = 32
print_info: n_head_kv        = 4
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: n_swa_pattern    = 1
print_info: n_embd_head_k    = 128
print_info: n_embd_head_v    = 128
print_info: n_gqa            = 8
print_info: n_embd_k_gqa     = 512
print_info: n_embd_v_gqa     = 512
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             = 6144
print_info: n_expert         = 128
print_info: n_expert_used    = 8
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: 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       = 30B.A3B
print_info: model params     = 30.53 B
print_info: general.name     = Qwen3-30B-A3B
print_info: n_ff_exp         = 768
print_info: vocab type       = BPE
print_info: n_vocab          = 151936
print_info: n_merges         = 151387
print_info: BOS token        = 11 ','
print_info: EOS token        = 151645 '<|im_end|>'
print_info: EOT token        = 151645 '<|im_end|>'
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 '<|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 48 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 49/49 layers to GPU
load_tensors:        ROCm0 model buffer size = 15803.55 MiB
load_tensors:        ROCm1 model buffer size = 14854.57 MiB
load_tensors:   CPU_Mapped model buffer size =   315.30 MiB
...................................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 16384
llama_context: n_ctx_per_seq = 16384
llama_context: n_batch       = 4096
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 (16384) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
llama_context:  ROCm_Host  output buffer size =     0.58 MiB
llama_kv_cache_unified: kv_size = 16384, type_k = 'f16', type_v = 'f16', n_layer = 48, can_shift = 1, padding = 32
llama_kv_cache_unified:      ROCm0 KV buffer size =   800.00 MiB
llama_kv_cache_unified:      ROCm1 KV buffer size =   736.00 MiB
llama_kv_cache_unified: KV self size  = 1536.00 MiB, K (f16):  768.00 MiB, V (f16):  768.00 MiB
llama_context: pipeline parallelism enabled (n_copies=4)
llama_context:      ROCm0 compute buffer size =  1192.01 MiB
llama_context:      ROCm1 compute buffer size =  1192.02 MiB
llama_context:  ROCm_Host compute buffer size =   132.02 MiB
llama_context: graph nodes  = 3126
llama_context: graph splits = 3
common_init_from_params: setting dry_penalty_last_n to ctx_size = 16384
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 = 16384
main: model loaded
main: chat template, chat_template: {%- if tools %}
    {{- '<|im_start|>system\n' }}
    {%- if messages[0].role == 'system' %}
        {{- messages[0].content + '\n\n' }}
    {%- endif %}
    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
    {%- for tool in tools %}
        {{- "\n" }}
        {{- tool | tojson }}
    {%- endfor %}
    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
    {%- if messages[0].role == 'system' %}
        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
    {%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for forward_message in messages %}
    {%- set index = (messages|length - 1) - loop.index0 %}
    {%- set message = messages[index] %}
    {%- set tool_start = '<tool_response>' %}
    {%- set tool_start_length = tool_start|length %}
    {%- set start_of_message = message.content[:tool_start_length] %}
    {%- set tool_end = '</tool_response>' %}
    {%- set tool_end_length = tool_end|length %}
    {%- set start_pos = (message.content|length) - tool_end_length %}
    {%- if start_pos < 0 %}
        {%- set start_pos = 0 %}
    {%- endif %}
    {%- set end_of_message = message.content[start_pos:] %}
    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
        {%- set ns.multi_step_tool = false %}
        {%- set ns.last_query_index = index %}
    {%- endif %}
{%- endfor %}
{%- for message in messages %}
    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
    {%- elif message.role == "assistant" %}
        {%- set content = message.content %}
        {%- set reasoning_content = '' %}
        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
            {%- set reasoning_content = message.reasoning_content %}
        {%- else %}
            {%- if '</think>' in message.content %}
                {%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
                {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
            {%- endif %}
        {%- endif %}
        {%- if loop.index0 > ns.last_query_index %}
            {%- if loop.last or (not loop.last and reasoning_content) %}
                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
            {%- else %}
                {{- '<|im_start|>' + message.role + '\n' + content }}
            {%- endif %}
        {%- else %}
            {{- '<|im_start|>' + message.role + '\n' + content }}
        {%- endif %}
        {%- if message.tool_calls %}
            {%- for tool_call in message.tool_calls %}
                {%- if (loop.first and content) or (not loop.first) %}
                    {{- '\n' }}
                {%- endif %}
                {%- if tool_call.function %}
                    {%- set tool_call = tool_call.function %}
                {%- endif %}
                {{- '<tool_call>\n{"name": "' }}
                {{- tool_call.name }}
                {{- '", "arguments": ' }}
                {%- if tool_call.arguments is string %}
                    {{- tool_call.arguments }}
                {%- else %}
                    {{- tool_call.arguments | tojson }}
                {%- endif %}
                {{- '}\n</tool_call>' }}
            {%- endfor %}
        {%- endif %}
        {{- '<|im_end|>\n' }}
    {%- elif message.role == "tool" %}
        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
            {{- '<|im_start|>user' }}
        {%- endif %}
        {{- '\n<tool_response>\n' }}
        {{- message.content }}
        {{- '\n</tool_response>' }}
        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
            {{- '<|im_end|>\n' }}
        {%- endif %}
    {%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
    {{- '<|im_start|>assistant\n' }}
    {%- if enable_thinking is defined and enable_thinking is false %}
        {{- '<think>\n\n</think>\n\n' }}
    {%- endif %}
{%- endif %}, example_format: '<|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
'
main: server is listening on http://[ip]:[port] - starting the main loop
srv  update_slots: all slots are idle
srv  log_server_r: request: GET /v1/models [ip] 200
srv  log_server_r: request: GET /v1/models [ip] 200
srv  log_server_r: request: GET /v1/models [ip] 200
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 = 16384, n_keep = 0, n_prompt_tokens = 13
slot update_slots: id  0 | task 0 | kv cache rm [0, end)
slot update_slots: id  0 | task 0 | prompt processing progress, n_past = 13, n_tokens = 13, progress = 1.000000
slot update_slots: id  0 | task 0 | prompt done, n_past = 13, n_tokens = 13
slot      release: id  0 | task 0 | stop processing: n_past = 863, truncated = 0
slot print_timing: id  0 | task 0 | 
prompt eval time =     154.13 ms /    13 tokens (   11.86 ms per token,    84.34 tokens per second)
       eval time =   14397.40 ms /   851 tokens (   16.92 ms per token,    59.11 tokens per second)
      total time =   14551.53 ms /   864 tokens
srv  update_slots: all slots are idle
srv  log_server_r: request: POST /v1/chat/completions [ip] 200
srv  log_server_r: request: GET /v1/models [ip] 200
srv  params_from_: Chat format: Content-only
slot launch_slot_: id  0 | task 852 | processing task
slot update_slots: id  0 | task 852 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 319
slot update_slots: id  0 | task 852 | kv cache rm [12, end)
slot update_slots: id  0 | task 852 | prompt processing progress, n_past = 319, n_tokens = 307, progress = 0.962382
slot update_slots: id  0 | task 852 | prompt done, n_past = 319, n_tokens = 307
llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:2073: GGML_ASSERT(!ggml_cuda_should_use_mmq(src0->type, cc, ne11) || ne00 % MATRIX_ROW_PADDING == 0) failed
Could not attach to process.  If your uid matches the uid of the target
process, check the setting of /proc/sys/kernel/yama/ptrace_scope, or try
again as the root user.  For more details, see /etc/sysctl.d/10-ptrace.conf
ptrace: Operation not permitted.
No stack.
The program is not being run.
Aborted (core dumped)

[joesixpaq]

I can confirm it, even though I get a different error message.

llama-server crashes immediately with exit code 134 (see below) if quantized k-cache is offloaded
AND
this model is used: DeepSeek-R1-UD-Q2_K_XL by unsloth

It works fine if the server is started without specifying k-cache quantization or setting it to the default f16.

It is fine to use --cache-type-k q8_0 with --no-kv-offload.
It would crash with --cache-type-k q4_0 alone too.

No crashes with DeepSeek-R1-UD-Q2_K_XL by unsloth which is a remake of the 3-month older DeepSeek-R1-UD-Q2_K_XL by unsloth

Crash log with the older DeepSeek-R1-UD-Q2_K_XL by unsloth

./llama-server
--port 8000
--model /mnt/AI/LLM/DeepSeek-R1-UD-Q2_K_XL/DeepSeek-R1-UD-Q2_K_XL-00001-of-00005.gguf
--n-gpu-layers 0
--ctx-size 16384
--no-mmap
--temp 0.6
--threads 8
--cache-type-k q4_0
--predict 16384
--batch-size 4096
--device CUDA0
--props

ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 CUDA devices:
Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
Device 1: Quadro M2000, compute capability 5.2, VMM: yes
build: 5287 (9070365) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
system info: n_threads = 8, n_threads_batch = 8, total_threads = 32

system_info: n_threads = 8 (n_threads_batch = 8) / 32 | 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: binding port with default address family
main: HTTP server is listening, hostname: 127.0.0.1, port: 8000, http threads: 31
main: loading model
srv load_model: loading model '/mnt/AI/LLM/DeepSeek-R1-UD-Q2_K_XL/DeepSeek-R1-UD-Q2_K_XL-00001-of-00005.gguf'
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3090) - 20352 MiB free
llama_model_loader: additional 4 GGUFs metadata loaded.
llama_model_loader: loaded meta data with 48 key-value pairs and 1025 tensors from /mnt/AI/LLM/DeepSeek-R1-UD-Q2_K_XL/DeepSeek-R1-UD-Q2_K_XL-00001-of-00005.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 = deepseek2
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = DeepSeek R1 BF16
llama_model_loader: - kv 3: general.quantized_by str = Unsloth
llama_model_loader: - kv 4: general.size_label str = 256x20B
llama_model_loader: - kv 5: general.repo_url str = https://huggingface.co/unsloth
llama_model_loader: - kv 6: deepseek2.block_count u32 = 61
llama_model_loader: - kv 7: deepseek2.context_length u32 = 163840
llama_model_loader: - kv 8: deepseek2.embedding_length u32 = 7168
llama_model_loader: - kv 9: deepseek2.feed_forward_length u32 = 18432
llama_model_loader: - kv 10: deepseek2.attention.head_count u32 = 128
llama_model_loader: - kv 11: deepseek2.attention.head_count_kv u32 = 128
llama_model_loader: - kv 12: deepseek2.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 13: deepseek2.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 14: deepseek2.expert_used_count u32 = 8
llama_model_loader: - kv 15: deepseek2.leading_dense_block_count u32 = 3
llama_model_loader: - kv 16: deepseek2.vocab_size u32 = 129280
llama_model_loader: - kv 17: deepseek2.attention.q_lora_rank u32 = 1536
llama_model_loader: - kv 18: deepseek2.attention.kv_lora_rank u32 = 512
llama_model_loader: - kv 19: deepseek2.attention.key_length u32 = 192
llama_model_loader: - kv 20: deepseek2.attention.value_length u32 = 128
llama_model_loader: - kv 21: deepseek2.expert_feed_forward_length u32 = 2048
llama_model_loader: - kv 22: deepseek2.expert_count u32 = 256
llama_model_loader: - kv 23: deepseek2.expert_shared_count u32 = 1
llama_model_loader: - kv 24: deepseek2.expert_weights_scale f32 = 2.500000
llama_model_loader: - kv 25: deepseek2.expert_weights_norm bool = true
llama_model_loader: - kv 26: deepseek2.expert_gating_func u32 = 2
llama_model_loader: - kv 27: deepseek2.rope.dimension_count u32 = 64
llama_model_loader: - kv 28: deepseek2.rope.scaling.type str = yarn
llama_model_loader: - kv 29: deepseek2.rope.scaling.factor f32 = 40.000000
llama_model_loader: - kv 30: deepseek2.rope.scaling.original_context_length u32 = 4096
llama_model_loader: - kv 31: deepseek2.rope.scaling.yarn_log_multiplier f32 = 0.100000
llama_model_loader: - kv 32: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 33: tokenizer.ggml.pre str = deepseek-v3
llama_model_loader: - kv 34: tokenizer.ggml.tokens arr[str,129280] = ["<｜begin▁of▁sentence｜>", "<�...
llama_model_loader: - kv 35: tokenizer.ggml.token_type arr[i32,129280] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 36: tokenizer.ggml.merges arr[str,127741] = ["Ġ t", "Ġ a", "i n", "Ġ Ġ", "h e...
llama_model_loader: - kv 37: tokenizer.ggml.bos_token_id u32 = 0
llama_model_loader: - kv 38: tokenizer.ggml.eos_token_id u32 = 1
llama_model_loader: - kv 39: tokenizer.ggml.padding_token_id u32 = 128815
llama_model_loader: - kv 40: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 41: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 42: tokenizer.chat_template str = {% if not add_generation_prompt is de...
llama_model_loader: - kv 43: general.quantization_version u32 = 2
llama_model_loader: - kv 44: general.file_type u32 = 10
llama_model_loader: - kv 45: split.no u16 = 0
llama_model_loader: - kv 46: split.tensors.count i32 = 1025
llama_model_loader: - kv 47: split.count u16 = 5
llama_model_loader: - type f32: 361 tensors
llama_model_loader: - type q2_K: 171 tensors
llama_model_loader: - type q3_K: 3 tensors
llama_model_loader: - type q4_K: 306 tensors
llama_model_loader: - type q6_K: 184 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q2_K - Medium
print_info: file size = 211.03 GiB (2.70 BPW)
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 819
load: token to piece cache size = 0.8223 MB
print_info: arch = deepseek2
print_info: vocab_only = 0
print_info: n_ctx_train = 163840
print_info: n_embd = 7168
print_info: n_layer = 61
print_info: n_head = 128
print_info: n_head_kv = 128
print_info: n_rot = 64
print_info: n_swa = 0
print_info: n_swa_pattern = 1
print_info: n_embd_head_k = 192
print_info: n_embd_head_v = 128
print_info: n_gqa = 1
print_info: n_embd_k_gqa = 24576
print_info: n_embd_v_gqa = 16384
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 = 18432
print_info: n_expert = 256
print_info: n_expert_used = 8
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = 0
print_info: rope scaling = yarn
print_info: freq_base_train = 10000.0
print_info: freq_scale_train = 0.025
print_info: n_ctx_orig_yarn = 4096
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 = 671B
print_info: model params = 671.03 B
print_info: general.name = DeepSeek R1 BF16
print_info: n_layer_dense_lead = 3
print_info: n_lora_q = 1536
print_info: n_lora_kv = 512
print_info: n_embd_head_k_mla = 0
print_info: n_embd_head_v_mla = 0
print_info: n_ff_exp = 2048
print_info: n_expert_shared = 1
print_info: expert_weights_scale = 2.5
print_info: expert_weights_norm = 1
print_info: expert_gating_func = sigmoid
print_info: rope_yarn_log_mul = 0.1000
print_info: vocab type = BPE
print_info: n_vocab = 129280
print_info: n_merges = 127741
print_info: BOS token = 0 '<｜begin▁of▁sentence｜>'
print_info: EOS token = 1 '<｜end▁of▁sentence｜>'
print_info: EOT token = 1 '<｜end▁of▁sentence｜>'
print_info: PAD token = 128815 '<｜PAD▁TOKEN｜>'
print_info: LF token = 201 'Ċ'
print_info: FIM PRE token = 128801 '<｜fim▁begin｜>'
print_info: FIM SUF token = 128800 '<｜fim▁hole｜>'
print_info: FIM MID token = 128802 '<｜fim▁end｜>'
print_info: EOG token = 1 '<｜end▁of▁sentence｜>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = false)
load_tensors: offloading 0 repeating layers to GPU
load_tensors: offloaded 0/62 layers to GPU
load_tensors: CUDA_Host model buffer size = 215601.95 MiB
load_tensors: CPU model buffer size = 497.11 MiB
....................................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 1
llama_context: n_ctx = 16384
llama_context: n_ctx_per_seq = 16384
llama_context: n_batch = 4096
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = 0
llama_context: freq_base = 10000.0
llama_context: freq_scale = 0.025
llama_context: n_ctx_per_seq (16384) < n_ctx_train (163840) -- the full capacity of the model will not be utilized
llama_context: CPU output buffer size = 0.49 MiB
llama_kv_cache_unified: kv_size = 16384, type_k = 'q4_0', type_v = 'f16', n_layer = 61, can_shift = 1, padding = 32
llama_kv_cache_unified: CPU KV buffer size = 44408.00 MiB
llama_kv_cache_unified: KV self size = 44408.00 MiB, K (q4_0): 13176.00 MiB, V (f16): 31232.00 MiB
llama_context: CUDA0 compute buffer size = 5017.50 MiB
llama_context: CUDA_Host compute buffer size = 112.01 MiB
llama_context: graph nodes = 4842
llama_context: graph splits = 1148 (with bs=512), 1 (with bs=1)
common_init_from_params: setting dry_penalty_last_n to ctx_size = 16384
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 = 16384
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='', is_first_sp=true) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}{%- endif %}{%- 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 'tool_calls' in message %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message['content'] is none %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + 'json' + '\n' + tool['function']['arguments'] + '\n' + '' + '<｜tool▁call▁end｜>'}}{%- else %}{{'<｜Assistant｜>' + message['content'] + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + 'json' + '\n' + tool['function']['arguments'] + '\n' + '' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + 'json' + '\n' + tool['function']['arguments'] + '\n' + '' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and 'tool_calls' not in message %}{%- 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 %}{{'<｜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://127.0.0.1:8000 - starting the main loop
srv update_slots: all slots are idle
srv log_server_r: request: GET / 127.0.0.1 200
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 = 16384, n_keep = 0, n_prompt_tokens = 45
slot update_slots: id 0 | task 0 | kv cache rm [0, end)
slot update_slots: id 0 | task 0 | prompt processing progress, n_past = 45, n_tokens = 45, progress = 1.000000
slot update_slots: id 0 | task 0 | prompt done, n_past = 45, n_tokens = 45
/home/ai/workspace/LLAMA_CPP/20250505-224936/llama.cpp/ggml/src/ggml-cuda/mmq.cu:94: GGML_ASSERT(ggml_is_contiguous(src0)) failed
Could not attach to process. If your uid matches the uid of the target
process, check the setting of /proc/sys/kernel/yama/ptrace_scope, or try
again as the root user. For more details, see /etc/sysctl.d/10-ptrace.conf
ptrace: Operation not permitted.
No stack.
The program is not being run.
Aborted (core dumped)
(base) xyz@pop-os:~/path/to/app$ echo $?
134

[JohannesGaessler]

Sorry, should be fixed by #13337 .