Built with LLAMA_CUDA, GPU visible but inference not utilizing GPU

[aleksas]

I have a NVIDIA GeForce RTX 4090. Built a https://github.com/ggerganov/llama.cpp -b b3011 inside a docker. nvidia-smi shows GPU - no problem here. Using Meta-Llama-3-8B-Instruct.Q8_0.gguf model from QuantFactory. But when doing inference the GPU is not used.

The code tag is 5month old, but that shouldn be an issue i guess.

main  -m ../whisper.cpp/models/Meta-Llama-3-8B-Instruct.Q8_0.gguf -c 512 -b 1024 -n 256 --keep 48     --repeat_penalty 1.0 --color -i     -r "User:" -f prompts/chat-with-bob.txt
Log start
main: build = 1 (197c006)
main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
main: seed  = 1728130330
llama_model_loader: loaded meta data with 27 key-value pairs and 291 tensors from ../whisper.cpp/models/Meta-Llama-3-8B-Instruct.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              = llama
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Models
llama_model_loader: - kv   3:                         general.size_label str              = 8.0B
llama_model_loader: - kv   4:                            general.license str              = llama3
llama_model_loader: - kv   5:                               general.tags arr[str,6]       = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv   6:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv   7:                          llama.block_count u32              = 32
llama_model_loader: - kv   8:                       llama.context_length u32              = 8192
llama_model_loader: - kv   9:                     llama.embedding_length u32              = 4096
llama_model_loader: - kv  10:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv  11:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv  12:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv  13:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv  14:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  15:                          general.file_type u32              = 7
llama_model_loader: - kv  16:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  17:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  18:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  19:                         tokenizer.ggml.pre str              = llama-bpe
llama_model_loader: - kv  20:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  21:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  22:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  23:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  24:                tokenizer.ggml.eos_token_id u32              = 128009
llama_model_loader: - kv  25:                    tokenizer.chat_template str              = {% set loop_messages = messages %}{% ...
llama_model_loader: - kv  26:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q8_0:  226 tensors
llm_load_vocab: special tokens definition check successful ( 256/128256 ).
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 128256
llm_load_print_meta: n_merges         = 280147
llm_load_print_meta: n_ctx_train      = 8192
llm_load_print_meta: n_embd           = 4096
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 8
llm_load_print_meta: n_layer          = 32
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 4
llm_load_print_meta: n_embd_k_gqa     = 1024
llm_load_print_meta: n_embd_v_gqa     = 1024
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 14336
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 0
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx  = 8192
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: model type       = 8B
llm_load_print_meta: model ftype      = Q8_0
llm_load_print_meta: model params     = 8.03 B
llm_load_print_meta: model size       = 7.95 GiB (8.50 BPW) 
llm_load_print_meta: general.name     = Models
llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:   no
ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes
llm_load_tensors: ggml ctx size =    0.15 MiB
llm_load_tensors: offloading 0 repeating layers to GPU
llm_load_tensors: offloaded 0/33 layers to GPU
llm_load_tensors:        CPU buffer size =  8137.64 MiB
.........................................................................................
llama_new_context_with_model: n_ctx      = 512
llama_new_context_with_model: n_batch    = 512
llama_new_context_with_model: n_ubatch   = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base  = 500000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init:  CUDA_Host KV buffer size =    64.00 MiB
llama_new_context_with_model: KV self size  =   64.00 MiB, K (f16):   32.00 MiB, V (f16):   32.00 MiB
llama_new_context_with_model:  CUDA_Host  output buffer size =     0.49 MiB
llama_new_context_with_model:      CUDA0 compute buffer size =   790.81 MiB
llama_new_context_with_model:  CUDA_Host compute buffer size =     9.01 MiB
llama_new_context_with_model: graph nodes  = 1030
llama_new_context_with_model: graph splits = 356

system_info: n_threads = 8 / 16 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | 
main: interactive mode on.
Reverse prompt: 'User:'
sampling: 
	repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000
	top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800
	mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampling order: 
CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temperature 
generate: n_ctx = 512, n_batch = 1024, n_predict = 256, n_keep = 48

build instructions

cmake -B /root/llama.cpp-build/ -S /root/llama.cpp/ \
     -DGGML_CUDA=ON \
     -DLLAMA_CUDA=ON \
     -DLLAMA_BUILD_EXAMPLES=ON \
     -DLLAMA_BUILD_TESTS=OFF \ 
 && cmake --build /root/llama.cpp-build/ --config Release --target install  -- -j 10

[danbev]

You will also need to specify the number of layers to be offloaded to the GPU by using --n-gpu-layers N.
More information can be found here.

[aleksas]

That worked perfectly.