docker: add perplexity and bench commands to full image

[rare-magma]

This adds arguments in the tools.sh script to execute the llama-bench and llama-perplexity tools in the docker full image.

run log:

podman run --privileged --name llama --replace -it --rm -v /var/home/user/downloads/models:/models --
net host --device /dev/dri/renderD128:/dev/dri/renderD128 --device /dev/dri/card1:/dev/dri/card1 --init localhost/llama-c
pp-vulkan:full --bench -m /models/qwen2.5-coder-3b-q8_0.gguf

ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = AMD Radeon RX 590 Series (RADV POLARIS10) (radv) | uma: 0 | fp16: 0 | warp size: 64 | matrix cores: none
| model                          |       size |     params | backend    | ngl |          test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ------------: | -------------------: |
| qwen2 3B Q8_0                  |   3.05 GiB |     3.09 B | Vulkan     |  99 |         pp512 |        515.60 ± 0.64 |
| qwen2 3B Q8_0                  |   3.05 GiB |     3.09 B | Vulkan     |  99 |         tg128 |         49.57 ± 0.36 |

build: 178a7eb9 (4562)

podman run --privileged --name llama --replace -it --rm -v /var/home/user/downloads/models:/models --
net host --device /dev/dri/renderD128:/dev/dri/renderD128 --device /dev/dri/card1:/dev/dri/card1 --init localhost/llama-c
pp-vulkan:full --perplexity -m /models/qwen2.5-coder-3b-q8_0.gguf

ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = AMD Radeon RX 590 Series (RADV POLARIS10) (radv) | uma: 0 | fp16: 0 | warp size: 64 | matrix cores: none
build: 4562 (178a7eb9) with cc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 for x86_64-linux-gnu
llama_model_load_from_file_impl: using device Vulkan0 (AMD Radeon RX 590 Series (RADV POLARIS10)) - 8192 MiB free
llama_model_loader: loaded meta data with 34 key-value pairs and 434 tensors from /models/qwen2.5-coder-3b-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              = qwen2
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen2.5 Coder 3B
llama_model_loader: - kv   3:                           general.basename str              = Qwen2.5-Coder
llama_model_loader: - kv   4:                         general.size_label str              = 3B
llama_model_loader: - kv   5:                            general.license str              = other
llama_model_loader: - kv   6:                       general.license.name str              = qwen-research
llama_model_loader: - kv   7:                       general.license.link str              = https://huggingface.co/Qwen/Qwen2.5-C...
llama_model_loader: - kv   8:                   general.base_model.count u32              = 1
llama_model_loader: - kv   9:                  general.base_model.0.name str              = Qwen2.5 3B
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/Qwen2.5-3B
llama_model_loader: - kv  12:                               general.tags arr[str,5]       = ["code", "qwen", "qwen-coder", "codeq...
llama_model_loader: - kv  13:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv  14:                          qwen2.block_count u32              = 36
llama_model_loader: - kv  15:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv  16:                     qwen2.embedding_length u32              = 2048
llama_model_loader: - kv  17:                  qwen2.feed_forward_length u32              = 11008
llama_model_loader: - kv  18:                 qwen2.attention.head_count u32              = 16
llama_model_loader: - kv  19:              qwen2.attention.head_count_kv u32              = 2
llama_model_loader: - kv  20:                       qwen2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  21:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  22:                          general.file_type u32              = 7
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 151643
llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  30:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  31:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  32:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  33:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  181 tensors
llama_model_loader: - type q8_0:  253 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q8_0
print_info: file size   = 3.05 GiB (8.50 BPW) 
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      = 32768
print_info: n_embd           = 2048
print_info: n_layer          = 36
print_info: n_head           = 16
print_info: n_head_kv        = 2
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            = 8
print_info: n_embd_k_gqa     = 256
print_info: n_embd_v_gqa     = 256
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: n_ff             = 11008
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  = 32768
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       = 3B
print_info: model params     = 3.09 B
print_info: general.name     = Qwen2.5 Coder 3B
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        = 151643 '<|endoftext|>'
print_info: EOT token        = 151645 '<|im_end|>'
print_info: PAD token        = 151643 '<|endoftext|>'
print_info: LF token         = 148848 'ÄĬ'
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: offloading 0 repeating layers to GPU
load_tensors: offloaded 0/37 layers to GPU
load_tensors:   CPU_Mapped model buffer size =  3127.59 MiB
llama_init_from_model: n_seq_max     = 4
llama_init_from_model: n_ctx         = 2048
llama_init_from_model: n_ctx_per_seq = 512
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 (512) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 2048, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 36, can_shift = 1
llama_kv_cache_init:        CPU KV buffer size =    72.00 MiB
llama_init_from_model: KV self size  =   72.00 MiB, K (f16):   36.00 MiB, V (f16):   36.00 MiB
llama_init_from_model:        CPU  output buffer size =     2.32 MiB
llama_init_from_model:    Vulkan0 compute buffer size =   616.05 MiB
llama_init_from_model: Vulkan_Host compute buffer size =     8.01 MiB
llama_init_from_model: graph nodes  = 1266
llama_init_from_model: graph splits = 508 (with bs=512), 1 (with bs=1)
common_init_from_params: setting dry_penalty_last_n to ctx_size = 2048
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)

system_info: n_threads = 8 (n_threads_batch = 8) / 16 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | OPENMP = 1 | AARCH64_REPACK = 1 | 
perplexity: tokenizing the input ..
perplexity: tokenization took 0.004 ms
perplexity: you need at least 1024 tokens to evaluate perplexity with a context of 512
perplexity: the data file you provided tokenizes to only 0 tokens

llama_perf_context_print:        load time =     503.39 ms
llama_perf_context_print: prompt eval time =       0.00 ms /     1 tokens (    0.00 ms per token,      inf tokens per second)
llama_perf_context_print:        eval time =       0.00 ms /     1 runs   (    0.00 ms per token,      inf tokens per second)
llama_perf_context_print:       total time =       0.12 ms /     2 tokens

[ericcurtin]

@rare-magma you are doing very similar things to the RamaLama project FWIW, in RamaLama it would be:

ramalama bench qwen2.5-coder

[ericcurtin]

I would certainly appreciate a PR in RamaLama that does:

ramalama perplexity qwen2.5-coder

https://github.com/containers/ramalama

[ericcurtin]

containers/ramalama#637