Confusion after running serve

[cdrage]

After running serve:

ramalama serve llama3
########################################################################################################################## 100.0%
INFO [                    main] build info | tid="0x1f51d4f40" timestamp=1724351882 build=3614 commit="a1631e53"
INFO [                    main] system info | tid="0x1f51d4f40" timestamp=1724351882 n_threads=8 n_threads_batch=-1 total_threads=10 system_info="AVX = 0 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 1 | SVE = 0 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | "
INFO [                    main] HTTP server is listening | tid="0x1f51d4f40" timestamp=1724351882 port="8080" n_threads_http="9" hostname="127.0.0.1"
INFO [                    main] loading model | tid="0x1f51d4f40" timestamp=1724351882 port="8080" n_threads_http="9" hostname="127.0.0.1"
llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from /Users/cdrage/.local/share/ramalama/models/ollama/llama3:latest (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.name str              = Meta-Llama-3-8B-Instruct
llama_model_loader: - kv   2:                          llama.block_count u32              = 32
llama_model_loader: - kv   3:                       llama.context_length u32              = 8192
llama_model_loader: - kv   4:                     llama.embedding_length u32              = 4096
llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv   6:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv   7:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv   8:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  10:                          general.file_type u32              = 2
llama_model_loader: - kv  11:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  12:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  14:                         tokenizer.ggml.pre str              = llama-bpe
llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  17:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 128009
llama_model_loader: - kv  20:                    tokenizer.chat_template str              = {% set loop_messages = messages %}{% ...
llama_model_loader: - kv  21:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q4_0:  225 tensors
llama_model_loader: - type q6_K:    1 tensors
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 0.8000 MB
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: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 8192
llm_load_print_meta: n_embd           = 4096
llm_load_print_meta: n_layer          = 32
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 8
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_swa            = 0
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_ctx_orig_yarn  = 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: ssm_dt_b_c_rms   = 0
llm_load_print_meta: model type       = 8B
llm_load_print_meta: model ftype      = Q4_0
llm_load_print_meta: model params     = 8.03 B
llm_load_print_meta: model size       = 4.33 GiB (4.64 BPW)
llm_load_print_meta: general.name     = Meta-Llama-3-8B-Instruct
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|>'
llm_load_print_meta: max token length = 256
llm_load_tensors: ggml ctx size =    0.27 MiB
ggml_backend_metal_log_allocated_size: allocated buffer, size =  4156.00 MiB, ( 4156.06 / 21845.34)
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 33/33 layers to GPU
llm_load_tensors:        CPU buffer size =   281.81 MiB
llm_load_tensors:      Metal buffer size =  4156.00 MiB
.......................................................................................
llama_new_context_with_model: n_ctx      = 8192
llama_new_context_with_model: n_batch    = 2048
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
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1 Pro
ggml_metal_init: picking default device: Apple M1 Pro
ggml_metal_init: using embedded metal library
ggml_metal_init: GPU name:   Apple M1 Pro
ggml_metal_init: GPU family: MTLGPUFamilyApple7  (1007)
ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_init: GPU family: MTLGPUFamilyMetal3  (5001)
ggml_metal_init: simdgroup reduction support   = true
ggml_metal_init: simdgroup matrix mul. support = true
ggml_metal_init: hasUnifiedMemory              = true
ggml_metal_init: recommendedMaxWorkingSetSize  = 22906.50 MB
llama_kv_cache_init:      Metal KV buffer size =  1024.00 MiB
llama_new_context_with_model: KV self size  = 1024.00 MiB, K (f16):  512.00 MiB, V (f16):  512.00 MiB
llama_new_context_with_model:        CPU  output buffer size =     0.98 MiB
llama_new_context_with_model:      Metal compute buffer size =   560.00 MiB
llama_new_context_with_model:        CPU compute buffer size =    24.01 MiB
llama_new_context_with_model: graph nodes  = 1030
llama_new_context_with_model: graph splits = 2
INFO [                    init] initializing slots | tid="0x1f51d4f40" timestamp=1724351893 n_slots=1
INFO [                    init] new slot | tid="0x1f51d4f40" timestamp=1724351893 id_slot=0 n_ctx_slot=8192
INFO [                    main] model loaded | tid="0x1f51d4f40" timestamp=1724351893
INFO [                    main] chat template | tid="0x1f51d4f40" timestamp=1724351893 chat_example="<|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHello<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nHi there<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHow are you?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n" built_in=true
INFO [            update_slots] all slots are idle | tid="0x1f51d4f40" timestamp=1724351893

I'm confused what to do next to be honest...

What are the next steps / CURL / webview to try it out?

Also, I am a bit confused too as to where or not this is a container being ran in the background or not, or whether this is native? I had thought that serve does it via containers only on the host system?

It ran, but there's nothing on podman ps

[ericcurtin]

You can curl... I'm assuming you have enough ram on your macbook pro....

It's late for me, but you could just play around with:

ramalama run llama3 to start

[ericcurtin]

You started a server on port 8080 there, it's llama.cpp under the hood

[cdrage]

You can curl... I'm assuming you have enough ram on your macbook pro....

It's late for me, but you could just play around with:

ramalama run llama3 to start

Ah that makes sense. I guess docs are on the way to show how to use it / simple hello world curl request

[ericcurtin]

There's some examples of what to curl here:

https://github.com/ggerganov/llama.cpp/blob/master/examples/server/README.md

if people want to duplicate some of these docs in ramalama, that's ok I guess.

[ericcurtin]

It's here:

https://github.com/containers/ramalama?tab=readme-ov-file#running-models

We should probably move that closer to the top of the README.md before Listing Models

Feel free to do that, I'll merge

[rhatdan]

We should also add this types of data to man ramalama-serve.

Eventually we want to look into adding ramalama to ai-lab-recipes, and hopefully the ramalama serve AI Models can be used for all of the different recipes.

[ericcurtin]

ramalama serve is this server:

https://github.com/ggerganov/llama.cpp/blob/master/examples/server/README.md

it's calling llama-server under the hood.