ramalama hangs when trying to shutdown

[tuananh]

its taking forever to shutdown so i have to kill the process & container manually.

[rhatdan]

What command were you running that failed to shutdown?

What version of ramalama are you running?

[benoitf]

@tuananh might be related to #753 ?

[rhatdan]

If this is, then you need to get new version of ramalama as well as new version of container image.

[tuananh]

What command were you running that failed to shutdown?

What version of ramalama are you running?

its serve command and im using latest version on arch repo

[rhatdan]

0.6.0 with what container image? Or are you using --no-container? The fix involved updating RamaLama and the version of llama.cpp.

You should see --init in the podman run command if you run with --debug flag.

[tuananh]

latest version on archlinux is 0.5.5

ramalama --version
ramalama version 0.5.5

the command i use is just ramalama serve <model> which I guess is the container version because I can see the container when running podman ps

[ericcurtin]

Didn't even realize we were packaged on arch neat:

https://aur.archlinux.org/packages/ramalama

I recommend logging this downstream with the Arch package maintainer, he should just update the package, it's fixed here upstream.

[tuananh]

So i update the package myself to 0.6.0 and it still hangs when i try to shut it down

command i use & its logs

ramalama serve ollama://deepseek-r1:32b
build: 4607 (aa6fb132) with cc (GCC) 11.5.0 20240719 (Red Hat 11.5.0-2) for x86_64-redhat-linux
system info: n_threads = 64, n_threads_batch = 64, total_threads = 128

system_info: n_threads = 64 (n_threads_batch = 64) / 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | OPENMP = 1 | AARCH64_REPACK = 1 |

main: HTTP server is listening, hostname: 0.0.0.0, port: 8080, http threads: 127
main: loading model
srv    load_model: loading model '/mnt/models/model.file'
llama_model_loader: loaded meta data with 26 key-value pairs and 771 tensors from /mnt/models/model.file (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              = DeepSeek R1 Distill Qwen 32B
llama_model_loader: - kv   3:                           general.basename str              = DeepSeek-R1-Distill-Qwen
llama_model_loader: - kv   4:                         general.size_label str              = 32B
llama_model_loader: - kv   5:                          qwen2.block_count u32              = 64
llama_model_loader: - kv   6:                       qwen2.context_length u32              = 131072
llama_model_loader: - kv   7:                     qwen2.embedding_length u32              = 5120
llama_model_loader: - kv   8:                  qwen2.feed_forward_length u32              = 27648
llama_model_loader: - kv   9:                 qwen2.attention.head_count u32              = 40
llama_model_loader: - kv  10:              qwen2.attention.head_count_kv u32              = 8
llama_model_loader: - kv  11:                       qwen2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  12:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  13:                          general.file_type u32              = 15
llama_model_loader: - kv  14:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  15:                         tokenizer.ggml.pre str              = deepseek-r1-qwen
llama_model_loader: - kv  16:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  17:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  18:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  19:                tokenizer.ggml.bos_token_id u32              = 151646                          llama_model_loader: - kv  20:                tokenizer.ggml.eos_token_id u32              = 151643
llama_model_loader: - kv  21:            tokenizer.ggml.padding_token_id u32              = 151643                          llama_model_loader: - kv  22:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  23:               tokenizer.ggml.add_eos_token bool             = false                           llama_model_loader: - kv  24:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
llama_model_loader: - kv  25:               general.quantization_version u32              = 2                               llama_model_loader: - type  f32:  321 tensors                 llama_model_loader: - type q4_K:  385 tensors                 llama_model_loader: - type q6_K:   65 tensors                 print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 18.48 GiB (4.85 BPW)
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
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      = 131072
print_info: n_embd           = 5120
print_info: n_layer          = 64
print_info: n_head           = 40
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            = 5                              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             = 27648                          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  = 131072
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       = 32B
print_info: model params     = 32.76 B                        print_info: general.name     = DeepSeek R1 Distill Qwen 32B
print_info: vocab type       = BPE                            print_info: n_vocab          = 152064
print_info: n_merges         = 151387                         print_info: BOS token        = 151646 '<｜begin▁of▁sentence｜>'                                                             print_info: EOS token        = 151643 '<｜end▁of▁sentence｜>'
print_info: EOT token        = 151643 '<｜end▁of▁sentence｜>' print_info: PAD token        = 151643 '<｜end▁of▁sentence｜>' 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 '<｜end▁of▁sentence｜>' 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:   CPU_Mapped model buffer size = 18926.01 MiB   llama_init_from_model: n_seq_max     = 1
llama_init_from_model: n_ctx         = 2048                   llama_init_from_model: n_ctx_per_seq = 2048                   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 (2048) < n_ctx_train (131072) -- 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 = 64, can_shift = 1
llama_kv_cache_init:        CPU KV buffer size =   512.00 MiB llama_init_from_model: KV self size  =  512.00 MiB, K (f16):  256.00 MiB, V (f16):  256.00 MiB
llama_init_from_model:        CPU  output buffer size =     0.58 MiB                                                        llama_init_from_model:        CPU compute buffer size =   307.00 MiB                                                        llama_init_from_model: graph nodes  = 2246
llama_init_from_model: graph splits = 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)
srv          init: initializing slots, n_slots = 1
slot         init: id  0 | task -1 | new slot n_ctx_slot = 2048                                                             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='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- 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 message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- 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｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-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 %}{{'\n<｜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://0.0.0.0:8080 - starting the main loop                                                   srv  update_slots: all slots are idle
request: GET / 10.0.0.245 200                                 request: GET /favicon.ico 10.0.0.245 404
slot launch_slot_: id  0 | task 0 | processing task
slot update_slots: id  0 | task 0 | new prompt, n_ctx_slot = 2048, n_keep = 0, n_prompt_tokens = 10                         slot update_slots: id  0 | task 0 | kv cache rm [0, end)
slot update_slots: id  0 | task 0 | prompt processing progress, n_past = 10, n_tokens = 10, progress = 1.000000
slot update_slots: id  0 | task 0 | prompt done, n_past = 10, n_tokens = 10
slot      release: id  0 | task 0 | stop processing: n_past = 392, truncated = 0
slot print_timing: id  0 | task 0 |
prompt eval time =     310.63 ms /    10 tokens (   31.06 ms per token,    32.19 tokens per second)
       eval time =   60010.24 ms /   383 tokens (  156.68 ms per token,     6.38 tokens per second)
      total time =   60320.87 ms /   393 tokens
srv  update_slots: all slots are idle
request: POST /v1/chat/completions 10.0.0.245 200
slot launch_slot_: id  0 | task 384 | processing task
slot update_slots: id  0 | task 384 | new prompt, n_ctx_slot = 2048, n_keep = 0, n_prompt_tokens = 27
slot update_slots: id  0 | task 384 | kv cache rm [10, end)
slot update_slots: id  0 | task 384 | prompt processing progress, n_past = 27, n_tokens = 17, progress = 0.629630
slot update_slots: id  0 | task 384 | prompt done, n_past = 27, n_tokens = 17
slot      release: id  0 | task 384 | stop processing: n_past = 122, truncated = 0
slot print_timing: id  0 | task 384 |
prompt eval time =     549.98 ms /    17 tokens (   32.35 ms per token,    30.91 tokens per second)
       eval time =   14705.24 ms /    96 tokens (  153.18 ms per token,     6.53 tokens per second)
      total time =   15255.22 ms /   113 tokens
srv  update_slots: all slots are idle
request: POST /v1/chat/completions 10.0.0.245 200

[benoitf]

AFAIK it's fixed in the main branch but not in 0.6.0 (at least this is what I experienced)

[tuananh]

AFAIK it's fixed in the main branch but not in 0.6.0 (at least this is what I experienced)

Thanks. I will try to build from main.

[tuananh]

@benoitf confirmed it's fixed on main. however, the port forwarding doesnt seem to work. i can't access 8080 from host but i guess it's another issue.

[rhatdan]

Please open a different issue on the 8080.

[tuananh]

Create a new issue for the port fwd #823