Misc. bug: "--parallel 1" initializes 4 slots, while docs say default is 1 #17989
Description
Name and Version
/llama-cli --version
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
version: 0 (unknown)
built with GNU 15.2.0 for Linux x86_64
Operating systems
Linux
Which llama.cpp modules do you know to be affected?
llama-server
Command line
./llama-server -m /home/mark/Models/Q8/Qwen3-0.6B-Q8_0/Qwen3-0.6B-Q8_0.gguf -c 8192 --port 9000 -np 1
./llama-server -m /home/mark/Models/Q8/Qwen3-0.6B-Q8_0/Qwen3-0.6B-Q8_0.gguf -c 8192 --port 9000 -np 2
./llama-server -m /home/mark/Models/Q8/Qwen3-0.6B-Q8_0/Qwen3-0.6B-Q8_0.gguf -c 8192 --port 9000 -np 3Problem description & steps to reproduce
When starting llama-server , the documentation in README.md states that:
- -np, --parallel N — number of parallel sequences to decode (default: 1)
However, in practice I am seeing 4 slots being initialized even when I explicitly set --parallel 1 . When I set --parallel 2 , the number of slots is correctly initialized to 2. This looks like either a bug or an inconsistency between the implementation and the documentation.
First Bad Commit
Sorry, no.
Relevant log output
mark@MarkPC:~/llama.cpp/llama.cpp-master$ ./llama-server -m /home/mark/Models/Q8/Qwen3-0.6B-Q8_0/Qwen3-0.6B-Q8_0.gguf -c 8192 --port 9000 -np 1
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
main: setting n_parallel = 4 and kv_unified = true (add -kvu to disable this)
build: 0 (unknown) with GNU 15.2.0 for Linux x86_64
system info: n_threads = 16, n_threads_batch = 16, total_threads = 32
system_info: n_threads = 16 (n_threads_batch = 16) / 32 | ROCm : NO_VMM = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 |
init: using 31 threads for HTTP server
start: binding port with default address family
main: loading model
srv load_model: loading model '/home/mark/Models/Q8/Qwen3-0.6B-Q8_0/Qwen3-0.6B-Q8_0.gguf'
llama_model_load_from_file_impl: using device ROCm0 (AMD Radeon Graphics) (0000:c6:00.0) - 31471 MiB free
llama_model_loader: loaded meta data with 28 key-value pairs and 310 tensors from /home/mark/Models/Q8/Qwen3-0.6B-Q8_0/Qwen3-0.6B-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 = qwen3
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Qwen3 0.6B Instruct
llama_model_loader: - kv 3: general.finetune str = Instruct
llama_model_loader: - kv 4: general.basename str = Qwen3
llama_model_loader: - kv 5: general.size_label str = 0.6B
llama_model_loader: - kv 6: qwen3.block_count u32 = 28
llama_model_loader: - kv 7: qwen3.context_length u32 = 40960
llama_model_loader: - kv 8: qwen3.embedding_length u32 = 1024
llama_model_loader: - kv 9: qwen3.feed_forward_length u32 = 3072
llama_model_loader: - kv 10: qwen3.attention.head_count u32 = 16
llama_model_loader: - kv 11: qwen3.attention.head_count_kv u32 = 8
llama_model_loader: - kv 12: qwen3.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 13: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 14: qwen3.attention.key_length u32 = 128
llama_model_loader: - kv 15: qwen3.attention.value_length u32 = 128
llama_model_loader: - kv 16: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 17: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 19: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 20: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 21: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 22: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 24: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 25: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
llama_model_loader: - kv 26: general.quantization_version u32 = 2
llama_model_loader: - kv 27: general.file_type u32 = 7
llama_model_loader: - type f32: 113 tensors
llama_model_loader: - type q8_0: 197 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q8_0
print_info: file size = 604.15 MiB (8.50 BPW)
load: printing all EOG tokens:
load: - 151643 ('<|endoftext|>')
load: - 151645 ('<|im_end|>')
load: - 151662 ('<|fim_pad|>')
load: - 151663 ('<|repo_name|>')
load: - 151664 ('<|file_sep|>')
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch = qwen3
print_info: vocab_only = 0
print_info: n_ctx_train = 40960
print_info: n_embd = 1024
print_info: n_embd_inp = 1024
print_info: n_layer = 28
print_info: n_head = 16
print_info: n_head_kv = 8
print_info: n_rot = 128
print_info: n_swa = 0
print_info: is_swa_any = 0
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 2
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-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 = 3072
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: n_expert_groups = 0
print_info: n_group_used = 0
print_info: causal attn = 1
print_info: pooling type = -1
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_yarn_log_mul= 0.0000
print_info: rope_finetuned = unknown
print_info: model type = 0.6B
print_info: model params = 596.05 M
print_info: general.name = Qwen3 0.6B Instruct
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 = 151645 '<|im_end|>'
print_info: EOT token = 151645 '<|im_end|>'
print_info: PAD token = 151643 '<|endoftext|>'
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 28 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 29/29 layers to GPU
load_tensors: CPU_Mapped model buffer size = 157.65 MiB
load_tensors: ROCm0 model buffer size = 604.15 MiB
.............................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 4
llama_context: n_ctx = 8192
llama_context: n_ctx_seq = 8192
llama_context: n_batch = 2048
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = auto
llama_context: kv_unified = true
llama_context: freq_base = 1000000.0
llama_context: freq_scale = 1
llama_context: n_ctx_seq (8192) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
llama_context: ROCm_Host output buffer size = 2.32 MiB
llama_kv_cache: ROCm0 KV buffer size = 896.00 MiB
llama_kv_cache: size = 896.00 MiB ( 8192 cells, 28 layers, 4/1 seqs), K (f16): 448.00 MiB, V (f16): 448.00 MiB
llama_context: Flash Attention was auto, set to enabled
llama_context: ROCm0 compute buffer size = 298.75 MiB
llama_context: ROCm_Host compute buffer size = 18.01 MiB
llama_context: graph nodes = 987
llama_context: graph splits = 2
common_init_from_params: added <|endoftext|> logit bias = -inf
common_init_from_params: added <|im_end|> logit bias = -inf
common_init_from_params: added <|fim_pad|> logit bias = -inf
common_init_from_params: added <|repo_name|> logit bias = -inf
common_init_from_params: added <|file_sep|> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 8192
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
srv init: initializing slots, n_slots = 4
slot init: id 0 | task -1 | new slot, n_ctx = 8192
slot init: id 1 | task -1 | new slot, n_ctx = 8192
slot init: id 2 | task -1 | new slot, n_ctx = 8192
slot init: id 3 | task -1 | new slot, n_ctx = 8192
srv init: prompt cache is enabled, size limit: 8192 MiB
srv init: use `--cache-ram 0` to disable the prompt cache
srv init: for more info see https://github.com/ggml-org/llama.cpp/pull/16391
srv init: thinking = 1
init: 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 index in range(ns.last_query_index, -1, -1) %}
{%- set message = messages[index] %}
{%- if ns.multi_step_tool and message.role == "user" and not('<tool_response>' in message.content and '</tool_response>' in message.content) %}
{%- 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>')[-1].lstrip('\n') %}
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].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: model loaded
main: server is listening on http://127.0.0.1:9000
main: starting the main loop...
srv update_slots: all slots are idle