Eval bug: Nemotron-H-47B-Reasoning no kv cache, always reprocesses prompt #16033
Closed as duplicate of#15677
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 CUDA devices:
Device 0: NVIDIA GeForce RTX 5090, compute capability 12.0, VMM: yes
load_backend: loaded CUDA backend from S:\llm\llama\ggml-cuda.dll
load_backend: loaded RPC backend from S:\llm\llama\ggml-rpc.dll
load_backend: loaded CPU backend from S:\llm\llama\ggml-cpu-alderlake.dll
version: 6641 (895329e)
built with clang version 19.1.5 for x86_64-pc-windows-msvc
Operating systems
Windows
GGML backends
CUDA
Hardware
Intel i9-12900K + 1x RTX 5090 32GB
Models
bartowski\nvidia_Nemotron-H-47B-Reasoning-128K-GGUF\nvidia_Nemotron-H-47B-Reasoning-128K-Q4_K_M.gguf
https://huggingface.co/bartowski/nvidia_Nemotron-H-47B-Reasoning-128K-GGUF
Problem description & steps to reproduce
when I run llama-server, it does not appear to respect the values for kv-cache; moreover, it reprocesses the prompt every time, which gets quite long in the end.
Particularly unrealistic values for kv cache (32768 context size):
llama_kv_cache: CUDA0 KV buffer size = 490.00 MiB
llama_kv_cache: size = 490.00 MiB ( 32768 cells, 5 layers, 1/1 seqs), K (f16): 320.00 MiB, V (q8_0): 170.00 MiB
And reprocessing every time:
slot update_slots: id 0 | task 275 | new prompt, n_ctx_slot = 32768, n_keep = 0, n_prompt_tokens = 1724
slot update_slots: id 0 | task 275 | n_past = 1682, cache_tokens.size() = 1716, seq_id = 0, pos_min = 1715, n_swa = 0
slot update_slots: id 0 | task 275 | forcing full prompt re-processing due to lack of cache data (likely due to SWA, see #13194 (comment))
slot update_slots: id 0 | task 275 | kv cache rm [0, end)
I tried with and without --swa-full, the result is still the same.
First Bad Commit
No response
Relevant log output
llama-server --model "s:\lmstudio\models\bartowski\nvidia_Nemotron-H-47B-Reasoning-128K-GGUF\nvidia_Nemotron-H-47B-Reasoning-128K-Q4_K_M.gguf" --alias "nvidia/Nemotron-H-47B-Reasoning-128K-Q4_K_M" --ctx-size 32768 --swa-full -ngl 999 -fa on -ctk f16 -ctv q8_0 --host 127.0.0.1 --port 8081 --no-mmap --jinja --threads 12
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 5090, compute capability 12.0, VMM: yes
load_backend: loaded CUDA backend from S:\llm\llama\ggml-cuda.dll
load_backend: loaded RPC backend from S:\llm\llama\ggml-rpc.dll
load_backend: loaded CPU backend from S:\llm\llama\ggml-cpu-alderlake.dll
build: 6641 (895329e1) with clang version 19.1.5 for x86_64-pc-windows-msvc
system info: n_threads = 12, n_threads_batch = 12, total_threads = 24
system_info: n_threads = 12 (n_threads_batch = 12) / 24 | CUDA : ARCHS = 500,610,700,750,800,860,890,1200 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 |
main: binding port with default address family
main: HTTP server is listening, hostname: 127.0.0.1, port: 8081, http threads: 23
main: loading model
srv load_model: loading model 's:\lmstudio\models\bartowski\nvidia_Nemotron-H-47B-Reasoning-128K-GGUF\nvidia_Nemotron-H-47B-Reasoning-128K-Q4_K_M.gguf'
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 5090) (0000:01:00.0) - 30841 MiB free
llama_model_loader: max stdio successfully set to 2048
llama_model_loader: loaded meta data with 48 key-value pairs and 577 tensors from s:\lmstudio\models\bartowski\nvidia_Nemotron-H-47B-Reasoning-128K-GGUF\nvidia_Nemotron-H-47B-Reasoning-128K-Q4_K_M.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 = nemotron_h
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Nemotron H 47B Reasoning 128K
llama_model_loader: - kv 3: general.finetune str = Reasoning-128k
llama_model_loader: - kv 4: general.basename str = Nemotron-H
llama_model_loader: - kv 5: general.size_label str = 47B
llama_model_loader: - kv 6: general.license str = other
llama_model_loader: - kv 7: general.license.name str = nvidia-internal-scientific-research-a...
llama_model_loader: - kv 8: general.license.link str = https://www.nvidia.com/en-us/agreemen...
llama_model_loader: - kv 9: general.tags arr[str,3] = ["nvidia", "pytorch", "text-generation"]
llama_model_loader: - kv 10: general.languages arr[str,1] = ["en"]
llama_model_loader: - kv 11: nemotron_h.block_count u32 = 98
llama_model_loader: - kv 12: nemotron_h.context_length u32 = 1048576
llama_model_loader: - kv 13: nemotron_h.embedding_length u32 = 8192
llama_model_loader: - kv 14: nemotron_h.feed_forward_length arr[i32,98] = [0, 30720, 0, 30720, 0, 30720, 0, 307...
llama_model_loader: - kv 15: nemotron_h.attention.head_count u32 = 64
llama_model_loader: - kv 16: nemotron_h.attention.head_count_kv arr[i32,98] = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...
llama_model_loader: - kv 17: nemotron_h.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 18: nemotron_h.attention.layer_norm_epsilon f32 = 0.000010
llama_model_loader: - kv 19: nemotron_h.vocab_size u32 = 131072
llama_model_loader: - kv 20: nemotron_h.rope.dimension_count u32 = 128
llama_model_loader: - kv 21: nemotron_h.ssm.conv_kernel u32 = 4
llama_model_loader: - kv 22: nemotron_h.ssm.state_size u32 = 256
llama_model_loader: - kv 23: nemotron_h.ssm.group_count u32 = 8
llama_model_loader: - kv 24: nemotron_h.ssm.inner_size u32 = 16384
llama_model_loader: - kv 25: nemotron_h.ssm.time_step_rank u32 = 256
llama_model_loader: - kv 26: nemotron_h.rope.scaling.finetuned bool = false
llama_model_loader: - kv 27: nemotron_h.attention.key_length u32 = 128
llama_model_loader: - kv 28: nemotron_h.attention.value_length u32 = 128
llama_model_loader: - kv 29: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 30: tokenizer.ggml.pre str = tekken
llama_model_loader: - kv 31: tokenizer.ggml.tokens arr[str,131072] = ["<unk>", "<s>", "</s>", "[INST]", "[...
llama_model_loader: - kv 32: tokenizer.ggml.token_type arr[i32,131072] = [3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, ...
llama_model_loader: - kv 33: tokenizer.ggml.merges arr[str,269443] = ["─а ─а", "─а t", "e r", "i n", "─а ─...
llama_model_loader: - kv 34: tokenizer.ggml.eos_token_id u32 = 11
llama_model_loader: - kv 35: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 36: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 37: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 38: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 39: tokenizer.ggml.add_sep_token bool = false
llama_model_loader: - kv 40: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 41: tokenizer.chat_template str = {{ '<SPECIAL_10>System\n' }}{%- if mes...
llama_model_loader: - kv 42: general.quantization_version u32 = 2
llama_model_loader: - kv 43: general.file_type u32 = 15
llama_model_loader: - kv 44: quantize.imatrix.file str = /models_out/Nemotron-H-47B-Reasoning-...
llama_model_loader: - kv 45: quantize.imatrix.dataset str = /training_dir/calibration_datav5.txt
llama_model_loader: - kv 46: quantize.imatrix.entries_count u32 = 206
llama_model_loader: - kv 47: quantize.imatrix.chunks_count u32 = 822
llama_model_loader: - type f32: 369 tensors
llama_model_loader: - type q4_K: 181 tensors
llama_model_loader: - type q6_K: 27 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 26.24 GiB (4.82 BPW)
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: printing all EOG tokens:
load: - 11 ('<SPECIAL_11>')
load: special tokens cache size = 1000
load: token to piece cache size = 0.8499 MB
print_info: arch = nemotron_h
print_info: vocab_only = 0
print_info: n_ctx_train = 1048576
print_info: n_embd = 8192
print_info: n_layer = 98
print_info: n_head = 64
print_info: n_head_kv = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
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 = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
print_info: n_embd_k_gqa = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1024, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1024, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1024, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1024, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1024, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
print_info: n_embd_v_gqa = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1024, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1024, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1024, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1024, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1024, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
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: f_attn_scale = 0.0e+00
print_info: n_ff = [0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 30720, 30720, 0, 0, 30720, 30720, 30720, 0, 30720, 0, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720, 0, 30720]
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 = -1
print_info: rope scaling = linear
print_info: freq_base_train = 10000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 1048576
print_info: rope_finetuned = unknown
print_info: ssm_d_conv = 4
print_info: ssm_d_inner = 16384
print_info: ssm_d_state = 256
print_info: ssm_dt_rank = 256
print_info: ssm_n_group = 8
print_info: ssm_dt_b_c_rms = 0
print_info: model type = ?B
print_info: model params = 46.79 B
print_info: general.name = Nemotron H 47B Reasoning 128K
print_info: vocab type = BPE
print_info: n_vocab = 131072
print_info: n_merges = 269443
print_info: BOS token = 1 '<s>'
print_info: EOS token = 11 '<SPECIAL_11>'
print_info: UNK token = 0 '<unk>'
print_info: PAD token = 0 '<unk>'
print_info: LF token = 1010 '─К'
print_info: EOG token = 11 '<SPECIAL_11>'
print_info: max token length = 150
load_tensors: loading model tensors, this can take a while... (mmap = false)
load_tensors: offloading 98 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 99/99 layers to GPU
load_tensors: CUDA0 model buffer size = 26298.37 MiB
load_tensors: CPU model buffer size = 576.00 MiB
................................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 1
llama_context: n_ctx = 32768
llama_context: n_ctx_per_seq = 32768
llama_context: n_batch = 2048
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = enabled
llama_context: kv_unified = false
llama_context: freq_base = 10000.0
llama_context: freq_scale = 1
llama_context: n_ctx_per_seq (32768) < n_ctx_train (1048576) -- the full capacity of the model will not be utilized
llama_context: CUDA_Host output buffer size = 0.50 MiB
llama_kv_cache: CUDA0 KV buffer size = 490.00 MiB
llama_kv_cache: size = 490.00 MiB ( 32768 cells, 5 layers, 1/1 seqs), K (f16): 320.00 MiB, V (q8_0): 170.00 MiB
llama_memory_recurrent: CUDA0 RS buffer size = 730.55 MiB
llama_memory_recurrent: size = 730.55 MiB ( 1 cells, 98 layers, 1 seqs), R (f32): 10.55 MiB, S (f32): 720.00 MiB
llama_context: CUDA0 compute buffer size = 304.24 MiB
llama_context: CUDA_Host compute buffer size = 176.01 MiB
llama_context: graph nodes = 2750
llama_context: graph splits = 13
common_init_from_params: added <SPECIAL_11> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 32768
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 = 32768
srv init: Enable thinking? 0
main: model loaded
main: chat template, chat_template: {{ '<SPECIAL_10>System
' }}{%- if messages and messages[0]['role'] == 'system' -%}{{ messages[0]['content'].strip() }}{%- endif -%}{% for message in (messages[1:] if messages[0]['role'] == 'system' else messages) %}{%- if message['role'] == 'user' -%}{{ '
<SPECIAL_11>User
' + message['content'].strip() + '
<SPECIAL_11>Assistant
' }}{%- if loop.last -%}{%- if messages[0]['role'] == 'system' -%}{%- if "{'reasoning': True}" in messages[0]['content'] -%}{{ '<think>
' }}{%- elif "{'reasoning': False}" in messages[0]['content'] -%}{{ '<think></think>' }}{%- endif -%}{%- endif -%}{%- endif -%}{%- elif message['role'] == 'assistant' -%}{{ message['content'].strip() }}{%- endif -%}{%- endfor -%}, example_format: '<SPECIAL_10>System
You are a helpful assistant
<SPECIAL_11>User
Hello
<SPECIAL_11>Assistant
Hi there
<SPECIAL_11>User
How are you?
<SPECIAL_11>Assistant
'
main: server is listening on http://127.0.0.1:8081 - starting the main loop
srv update_slots: all slots are idle
common_sampler_types_from_names: unable to match sampler by name 'tfs_z'
common_sampler_types_from_names: unable to match sampler by name 'typical_p'
slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = -1
slot launch_slot_: id 0 | task 0 | processing task
slot update_slots: id 0 | task 0 | new prompt, n_ctx_slot = 32768, n_keep = 0, n_prompt_tokens = 1060
slot update_slots: id 0 | task 0 | kv cache rm [0, end)
slot update_slots: id 0 | task 0 | prompt processing progress, n_past = 1060, n_tokens = 1060, progress = 1.000000
slot update_slots: id 0 | task 0 | prompt done, n_past = 1060, n_tokens = 1060
slot release: id 0 | task 0 | stop processing: n_past = 1178, truncated = 0
slot print_timing: id 0 | task 0 |
prompt eval time = 1922.90 ms / 1060 tokens ( 1.81 ms per token, 551.25 tokens per second)
eval time = 3855.63 ms / 119 tokens ( 32.40 ms per token, 30.86 tokens per second)
total time = 5778.53 ms / 1179 tokens
srv update_slots: all slots are idle
srv log_server_r: request: POST /completion 127.0.0.1 200
common_sampler_types_from_names: unable to match sampler by name 'tfs_z'
common_sampler_types_from_names: unable to match sampler by name 'typical_p'
slot get_availabl: id 0 | task 0 | selected slot by lcs similarity, lcs_len = 1059, similarity = 0.899 (> 0.100 thold)
slot launch_slot_: id 0 | task 120 | processing task
slot update_slots: id 0 | task 120 | new prompt, n_ctx_slot = 32768, n_keep = 0, n_prompt_tokens = 1557
slot update_slots: id 0 | task 120 | n_past = 1059, cache_tokens.size() = 1178, seq_id = 0, pos_min = 1177, n_swa = 0
slot update_slots: id 0 | task 120 | forcing full prompt re-processing due to lack of cache data (likely due to SWA, see https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
slot update_slots: id 0 | task 120 | kv cache rm [0, end)
slot update_slots: id 0 | task 120 | prompt processing progress, n_past = 1557, n_tokens = 1557, progress = 1.000000
slot update_slots: id 0 | task 120 | prompt done, n_past = 1557, n_tokens = 1557
slot release: id 0 | task 120 | stop processing: n_past = 1675, truncated = 0
slot print_timing: id 0 | task 120 |
prompt eval time = 3374.52 ms / 1557 tokens ( 2.17 ms per token, 461.40 tokens per second)
eval time = 4065.55 ms / 119 tokens ( 34.16 ms per token, 29.27 tokens per second)
total time = 7440.07 ms / 1676 tokens
srv update_slots: all slots are idle
srv log_server_r: request: POST /completion 127.0.0.1 200
common_sampler_types_from_names: unable to match sampler by name 'tfs_z'
common_sampler_types_from_names: unable to match sampler by name 'typical_p'
slot get_availabl: id 0 | task 120 | selected slot by lcs similarity, lcs_len = 1556, similarity = 0.929 (> 0.100 thold)
slot launch_slot_: id 0 | task 240 | processing task
slot update_slots: id 0 | task 240 | new prompt, n_ctx_slot = 32768, n_keep = 0, n_prompt_tokens = 1683
slot update_slots: id 0 | task 240 | n_past = 1556, cache_tokens.size() = 1675, seq_id = 0, pos_min = 1674, n_swa = 0
slot update_slots: id 0 | task 240 | forcing full prompt re-processing due to lack of cache data (likely due to SWA, see https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
slot update_slots: id 0 | task 240 | kv cache rm [0, end)
slot update_slots: id 0 | task 240 | prompt processing progress, n_past = 1683, n_tokens = 1683, progress = 1.000000
slot update_slots: id 0 | task 240 | prompt done, n_past = 1683, n_tokens = 1683
slot release: id 0 | task 240 | stop processing: n_past = 1716, truncated = 0
slot print_timing: id 0 | task 240 |
prompt eval time = 3883.47 ms / 1683 tokens ( 2.31 ms per token, 433.38 tokens per second)
eval time = 1148.31 ms / 34 tokens ( 33.77 ms per token, 29.61 tokens per second)
total time = 5031.77 ms / 1717 tokens
srv update_slots: all slots are idle
srv log_server_r: request: POST /completion 127.0.0.1 200
common_sampler_types_from_names: unable to match sampler by name 'tfs_z'
common_sampler_types_from_names: unable to match sampler by name 'typical_p'
slot get_availabl: id 0 | task 240 | selected slot by lcs similarity, lcs_len = 1682, similarity = 0.980 (> 0.100 thold)
slot launch_slot_: id 0 | task 275 | processing task
slot update_slots: id 0 | task 275 | new prompt, n_ctx_slot = 32768, n_keep = 0, n_prompt_tokens = 1724
slot update_slots: id 0 | task 275 | n_past = 1682, cache_tokens.size() = 1716, seq_id = 0, pos_min = 1715, n_swa = 0
slot update_slots: id 0 | task 275 | forcing full prompt re-processing due to lack of cache data (likely due to SWA, see https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
slot update_slots: id 0 | task 275 | kv cache rm [0, end)
slot update_slots: id 0 | task 275 | prompt processing progress, n_past = 1724, n_tokens = 1724, progress = 1.000000
slot update_slots: id 0 | task 275 | prompt done, n_past = 1724, n_tokens = 1724
slot release: id 0 | task 275 | stop processing: n_past = 1756, truncated = 0
slot print_timing: id 0 | task 275 |
prompt eval time = 4176.55 ms / 1724 tokens ( 2.42 ms per token, 412.78 tokens per second)
eval time = 1108.56 ms / 33 tokens ( 33.59 ms per token, 29.77 tokens per second)
total time = 5285.10 ms / 1757 tokens
srv update_slots: all slots are idle
srv log_server_r: request: POST /completion 127.0.0.1 200