643 lines
60 KiB
Plaintext
643 lines
60 KiB
Plaintext
llama_bin_run\llama-server.exe : ggml_cuda_init: found 2 CUDA
|
|
devices (Total VRAM: 24575 MiB):
|
|
위치 줄:1 문자:1
|
|
+ llama_bin_run\llama-server.exe --model "models\Q4_K_M\Qwen3.
|
|
5-122B-A1 ...
|
|
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
~~~~~~~~~
|
|
+ CategoryInfo : NotSpecified: (ggml_cuda_init:.
|
|
..AM: 24575 MiB)::String) [], RemoteException
|
|
+ FullyQualifiedErrorId : NativeCommandError
|
|
|
|
Device 0: NVIDIA GeForce RTX 3060, compute capability 8.6, V
|
|
MM: yes, VRAM: 12287 MiB
|
|
Device 1: NVIDIA GeForce RTX 3060, compute capability 8.6, V
|
|
MM: yes, VRAM: 12287 MiB
|
|
load_backend: loaded CUDA backend from C:\Users\Variet-Worker\
|
|
Desktop\variet-llm\llama_bin_run\ggml-cuda.dll
|
|
load_backend: loaded RPC backend from C:\Users\Variet-Worker\D
|
|
esktop\variet-llm\llama_bin_run\ggml-rpc.dll
|
|
load_backend: loaded CPU backend from C:\Users\Variet-Worker\D
|
|
esktop\variet-llm\llama_bin_run\ggml-cpu-haswell.dll
|
|
system info: n_threads = 6, n_threads_batch = 6, total_threads
|
|
= 16
|
|
|
|
system_info: n_threads = 6 (n_threads_batch = 6) / 16 | CUDA :
|
|
ARCHS = 500,610,700,750,800,860,890 | USE_GRAPHS = 1 | PEER_M
|
|
AX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | A
|
|
VX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPEN
|
|
MP = 1 | REPACK = 1 |
|
|
|
|
Running without SSL
|
|
init: using 15 threads for HTTP server
|
|
start: binding port with default address family
|
|
main: loading model
|
|
srv load_model: loading model 'models\Q4_K_M\Qwen3.5-122B-A
|
|
10B-Q4_K_M-00001-of-00003.gguf'
|
|
common_init_result: fitting params to device memory, for bugs
|
|
during this step try to reproduce them with -fit off, or provi
|
|
de --verbose logs if the bug only occurs with -fit on
|
|
llama_params_fit_impl: projected memory use with initial param
|
|
eters [MiB]:
|
|
llama_params_fit_impl: - CUDA0 (NVIDIA GeForce RTX 3060): 1
|
|
2287 total, 37929 used, -26764 free vs. target of 1024
|
|
llama_params_fit_impl: - CUDA1 (NVIDIA GeForce RTX 3060): 1
|
|
2287 total, 35760 used, -24592 free vs. target of 1024
|
|
llama_params_fit_impl: projected to use 73690 MiB of device me
|
|
mory vs. 22333 MiB of free device memory
|
|
llama_params_fit_impl: cannot meet free memory targets on all
|
|
devices, need to use 53405 MiB less in total
|
|
llama_params_fit_impl: context size set by user to 32768 -> no
|
|
change
|
|
llama_params_fit_impl: with only dense weights in device memor
|
|
y there is a total surplus of 13058 MiB
|
|
llama_params_fit_impl: filling dense-only layers back-to-front
|
|
:
|
|
llama_params_fit_impl: - CUDA1 (NVIDIA GeForce RTX 3060): 49
|
|
layers, 7651 MiB used, 3516 MiB free
|
|
llama_params_fit_impl: - CUDA0 (NVIDIA GeForce RTX 3060): 0
|
|
layers, 966 MiB used, 10198 MiB free
|
|
llama_params_fit_impl: converting dense-only layers to full la
|
|
yers and filling them front-to-back with overflow to next devi
|
|
ce/system memory:
|
|
llama_params_fit_impl: - CUDA0 (NVIDIA GeForce RTX 3060): 7
|
|
layers ( 1 overflowing), 10055 MiB used, 1109 MiB free
|
|
llama_params_fit_impl: - CUDA1 (NVIDIA GeForce RTX 3060): 42
|
|
layers (40 overflowing), 9786 MiB used, 1381 MiB free
|
|
llama_params_fit: successfully fit params to free device memor
|
|
y
|
|
llama_params_fit: fitting params to free memory took 0.47 seco
|
|
nds
|
|
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA Ge
|
|
Force RTX 3060) (0000:04:00.0) - 11245 MiB free
|
|
llama_model_load_from_file_impl: using device CUDA1 (NVIDIA Ge
|
|
Force RTX 3060) (0000:06:00.0) - 11240 MiB free
|
|
llama_model_loader: additional 2 GGUFs metadata loaded.
|
|
llama_model_loader: loaded meta data with 55 key-value pairs a
|
|
nd 879 tensors from models\Q4_K_M\Qwen3.5-122B-A10B-Q4_K_M-000
|
|
01-of-00003.gguf (version GGUF V3 (latest))
|
|
llama_model_loader: Dumping metadata keys/values. Note: KV ove
|
|
rrides do not apply in this output.
|
|
llama_model_loader: - kv 0: general.ar
|
|
chitecture str = qwen35moe
|
|
llama_model_loader: - kv 1: ge
|
|
neral.type str = model
|
|
llama_model_loader: - kv 2: general.samp
|
|
ling.top_k i32 = 20
|
|
llama_model_loader: - kv 3: general.samp
|
|
ling.top_p f32 = 0.950000
|
|
llama_model_loader: - kv 4: general.sam
|
|
pling.temp f32 = 0.600000
|
|
llama_model_loader: - kv 5: ge
|
|
neral.name str = Qwen3.5-122B-A10B
|
|
llama_model_loader: - kv 6: genera
|
|
l.basename str = Qwen3.5-122B-A10B
|
|
llama_model_loader: - kv 7: general.qu
|
|
antized_by str = Unsloth
|
|
llama_model_loader: - kv 8: general.
|
|
size_label str = 122B-A10B
|
|
llama_model_loader: - kv 9: gener
|
|
al.license str = apache-2.0
|
|
llama_model_loader: - kv 10: general.li
|
|
cense.link str = https://huggingface.co/Qwen/Qwen
|
|
3.5-1...
|
|
llama_model_loader: - kv 11: genera
|
|
l.repo_url str = https://huggingface.co/unsloth
|
|
llama_model_loader: - kv 12: general.base_m
|
|
odel.count u32 = 1
|
|
llama_model_loader: - kv 13: general.base_mo
|
|
del.0.name str = Qwen3.5 122B A10B
|
|
llama_model_loader: - kv 14: general.base_model.0.or
|
|
ganization str = Qwen
|
|
llama_model_loader: - kv 15: general.base_model.
|
|
0.repo_url str = https://huggingface.co/Qwen/Qwen
|
|
3.5-1...
|
|
llama_model_loader: - kv 16: ge
|
|
neral.tags arr[str,2] = ["unsloth", "image-text-to-text"
|
|
]
|
|
llama_model_loader: - kv 17: qwen35moe.b
|
|
lock_count u32 = 48
|
|
llama_model_loader: - kv 18: qwen35moe.cont
|
|
ext_length u32 = 262144
|
|
llama_model_loader: - kv 19: qwen35moe.embedd
|
|
ing_length u32 = 3072
|
|
llama_model_loader: - kv 20: qwen35moe.attention.
|
|
head_count u32 = 32
|
|
llama_model_loader: - kv 21: qwen35moe.attention.hea
|
|
d_count_kv u32 = 2
|
|
llama_model_loader: - kv 22: qwen35moe.rope.dimensio
|
|
n_sections arr[i32,4] = [11, 11, 10, 0]
|
|
llama_model_loader: - kv 23: qwen35moe.rope
|
|
.freq_base f32 = 10000000.000000
|
|
llama_model_loader: - kv 24: qwen35moe.attention.layer_norm_r
|
|
ms_epsilon f32 = 0.000001
|
|
llama_model_loader: - kv 25: qwen35moe.ex
|
|
pert_count u32 = 256
|
|
llama_model_loader: - kv 26: qwen35moe.expert_
|
|
used_count u32 = 8
|
|
llama_model_loader: - kv 27: qwen35moe.attention.
|
|
key_length u32 = 256
|
|
llama_model_loader: - kv 28: qwen35moe.attention.va
|
|
lue_length u32 = 256
|
|
llama_model_loader: - kv 29: qwen35moe.expert_feed_forw
|
|
ard_length u32 = 1024
|
|
llama_model_loader: - kv 30: qwen35moe.expert_shared_feed_for
|
|
ward_length u32 = 1024
|
|
llama_model_loader: - kv 31: qwen35moe.ssm.c
|
|
onv_kernel u32 = 4
|
|
llama_model_loader: - kv 32: qwen35moe.ssm.
|
|
state_size u32 = 128
|
|
llama_model_loader: - kv 33: qwen35moe.ssm.g
|
|
roup_count u32 = 16
|
|
llama_model_loader: - kv 34: qwen35moe.ssm.time
|
|
_step_rank u32 = 64
|
|
llama_model_loader: - kv 35: qwen35moe.ssm.
|
|
inner_size u32 = 8192
|
|
llama_model_loader: - kv 36: qwen35moe.full_attentio
|
|
n_interval u32 = 4
|
|
llama_model_loader: - kv 37: qwen35moe.rope.dimen
|
|
sion_count u32 = 64
|
|
llama_model_loader: - kv 38: tokenizer.
|
|
ggml.model str = gpt2
|
|
llama_model_loader: - kv 39: tokenize
|
|
r.ggml.pre str = qwen35
|
|
llama_model_loader: - kv 40: tokenizer.g
|
|
gml.tokens arr[str,248320] = ["!", "\"", "#", "$", "%", "&",
|
|
"'", ...
|
|
llama_model_loader: - kv 41: tokenizer.ggml.
|
|
token_type arr[i32,248320] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1
|
|
, 1, ...
|
|
llama_model_loader: - kv 42: tokenizer.g
|
|
gml.merges arr[str,247587] = ["휔 휔", "휔휔 휔휔", "i n", "휔 t",..
|
|
.
|
|
llama_model_loader: - kv 43: tokenizer.ggml.eo
|
|
s_token_id u32 = 248046
|
|
llama_model_loader: - kv 44: tokenizer.ggml.paddin
|
|
g_token_id u32 = 248055
|
|
llama_model_loader: - kv 45: tokenizer.cha
|
|
t_template str = {%- set image_count = namespace(
|
|
value...
|
|
llama_model_loader: - kv 46: general.quantizati
|
|
on_version u32 = 2
|
|
llama_model_loader: - kv 47: general
|
|
.file_type u32 = 15
|
|
llama_model_loader: - kv 48: quantize.im
|
|
atrix.file str = Qwen3.5-122B-A10B-GGUF/imatrix_u
|
|
nslot...
|
|
llama_model_loader: - kv 49: quantize.imatr
|
|
ix.dataset str = unsloth_calibration_Qwen3.5-122B
|
|
-A10B...
|
|
llama_model_loader: - kv 50: quantize.imatrix.ent
|
|
ries_count u32 = 612
|
|
llama_model_loader: - kv 51: quantize.imatrix.ch
|
|
unks_count u32 = 76
|
|
llama_model_loader: - kv 52:
|
|
split.no u16 = 0
|
|
llama_model_loader: - kv 53: split.ten
|
|
sors.count i32 = 879
|
|
llama_model_loader: - kv 54: s
|
|
plit.count u16 = 3
|
|
llama_model_loader: - type f32: 361 tensors
|
|
llama_model_loader: - type q8_0: 373 tensors
|
|
llama_model_loader: - type q4_K: 96 tensors
|
|
llama_model_loader: - type q5_K: 48 tensors
|
|
llama_model_loader: - type q6_K: 1 tensors
|
|
print_info: file format = GGUF V3 (latest)
|
|
print_info: file type = Q4_K - Medium
|
|
print_info: file size = 71.27 GiB (5.01 BPW)
|
|
load: 0 unused tokens
|
|
load: printing all EOG tokens:
|
|
load: - 248044 ('<|endoftext|>')
|
|
load: - 248046 ('<|im_end|>')
|
|
load: - 248063 ('<|fim_pad|>')
|
|
load: - 248064 ('<|repo_name|>')
|
|
load: - 248065 ('<|file_sep|>')
|
|
load: special tokens cache size = 33
|
|
load: token to piece cache size = 1.7581 MB
|
|
print_info: arch = qwen35moe
|
|
print_info: vocab_only = 0
|
|
print_info: no_alloc = 0
|
|
print_info: n_ctx_train = 262144
|
|
print_info: n_embd = 3072
|
|
print_info: n_embd_inp = 3072
|
|
print_info: n_layer = 48
|
|
print_info: n_head = 32
|
|
print_info: n_head_kv = 2
|
|
print_info: n_rot = 64
|
|
print_info: n_swa = 0
|
|
print_info: is_swa_any = 0
|
|
print_info: n_embd_head_k = 256
|
|
print_info: n_embd_head_v = 256
|
|
print_info: n_gqa = 16
|
|
print_info: n_embd_k_gqa = 512
|
|
print_info: n_embd_v_gqa = 512
|
|
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 = 0
|
|
print_info: n_expert = 256
|
|
print_info: n_expert_used = 8
|
|
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 = 40
|
|
print_info: rope scaling = linear
|
|
print_info: freq_base_train = 10000000.0
|
|
print_info: freq_scale_train = 1
|
|
print_info: n_ctx_orig_yarn = 262144
|
|
print_info: rope_yarn_log_mul = 0.0000
|
|
print_info: rope_finetuned = unknown
|
|
print_info: mrope sections = [11, 11, 10, 0]
|
|
print_info: ssm_d_conv = 4
|
|
print_info: ssm_d_inner = 8192
|
|
print_info: ssm_d_state = 128
|
|
print_info: ssm_dt_rank = 64
|
|
print_info: ssm_n_group = 16
|
|
print_info: ssm_dt_b_c_rms = 0
|
|
print_info: model type = 122B.A10B
|
|
print_info: model params = 122.11 B
|
|
print_info: general.name = Qwen3.5-122B-A10B
|
|
print_info: vocab type = BPE
|
|
print_info: n_vocab = 248320
|
|
print_info: n_merges = 247587
|
|
print_info: BOS token = 11 ','
|
|
print_info: EOS token = 248046 '<|im_end|>'
|
|
print_info: EOT token = 248046 '<|im_end|>'
|
|
print_info: PAD token = 248055 '<|vision_pad|>'
|
|
print_info: LF token = 198 '훹'
|
|
print_info: FIM PRE token = 248060 '<|fim_prefix|>'
|
|
print_info: FIM SUF token = 248062 '<|fim_suffix|>'
|
|
print_info: FIM MID token = 248061 '<|fim_middle|>'
|
|
print_info: FIM PAD token = 248063 '<|fim_pad|>'
|
|
print_info: FIM REP token = 248064 '<|repo_name|>'
|
|
print_info: FIM SEP token = 248065 '<|file_sep|>'
|
|
print_info: EOG token = 248044 '<|endoftext|>'
|
|
print_info: EOG token = 248046 '<|im_end|>'
|
|
print_info: EOG token = 248063 '<|fim_pad|>'
|
|
print_info: EOG token = 248064 '<|repo_name|>'
|
|
print_info: EOG token = 248065 '<|file_sep|>'
|
|
print_info: max token length = 256
|
|
load_tensors: loading model tensors, this can take a while...
|
|
(mmap = true, direct_io = false)
|
|
llama_model_loader: tensor overrides to CPU are used with mmap
|
|
enabled - consider using --no-mmap for better performance
|
|
load_tensors: offloading output layer to GPU
|
|
load_tensors: offloading 47 repeating layers to GPU
|
|
load_tensors: offloaded 49/49 layers to GPU
|
|
load_tensors: CPU_Mapped model buffer size = 47000.12 MiB
|
|
load_tensors: CPU_Mapped model buffer size = 25271.75 MiB
|
|
load_tensors: CUDA0 model buffer size = 9046.32 MiB
|
|
load_tensors: CUDA1 model buffer size = 8860.98 MiB
|
|
..............................................................
|
|
......................................
|
|
common_init_result: added <|endoftext|> logit bias = -inf
|
|
common_init_result: added <|im_end|> logit bias = -inf
|
|
common_init_result: added <|fim_pad|> logit bias = -inf
|
|
common_init_result: added <|repo_name|> logit bias = -inf
|
|
common_init_result: added <|file_sep|> logit bias = -inf
|
|
llama_context: constructing llama_context
|
|
llama_context: n_seq_max = 1
|
|
llama_context: n_ctx = 32768
|
|
llama_context: n_ctx_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 = 10000000.0
|
|
llama_context: freq_scale = 1
|
|
llama_context: n_ctx_seq (32768) < n_ctx_train (262144) -- the
|
|
full capacity of the model will not be utilized
|
|
llama_context: CUDA_Host output buffer size = 0.95 MiB
|
|
llama_kv_cache: CUDA0 KV buffer size = 18.00 MiB
|
|
llama_kv_cache: CUDA1 KV buffer size = 198.00 MiB
|
|
llama_kv_cache: size = 216.00 MiB ( 32768 cells, 12 layers,
|
|
1/1 seqs), K (q4_0): 108.00 MiB, V (q4_0): 108.00 MiB
|
|
llama_kv_cache: attn_rot_k = 1
|
|
llama_kv_cache: attn_rot_v = 1
|
|
llama_memory_recurrent: CUDA0 RS buffer size = 24.84 M
|
|
iB
|
|
llama_memory_recurrent: CUDA1 RS buffer size = 124.22 M
|
|
iB
|
|
llama_memory_recurrent: size = 149.06 MiB ( 1 cells, 48
|
|
layers, 1 seqs), R (f32): 5.06 MiB, S (f32): 144.00 MiB
|
|
sched_reserve: reserving ...
|
|
sched_reserve: resolving fused Gated Delta Net support:
|
|
sched_reserve: fused Gated Delta Net (autoregressive) enabled
|
|
sched_reserve: fused Gated Delta Net (chunked) enabled
|
|
sched_reserve: CUDA0 compute buffer size = 966.50 MiB
|
|
sched_reserve: CUDA1 compute buffer size = 603.42 MiB
|
|
sched_reserve: CUDA_Host compute buffer size = 76.29 MiB
|
|
sched_reserve: graph nodes = 4617
|
|
sched_reserve: graph splits = 164 (with bs=512), 81 (with bs=1
|
|
)
|
|
sched_reserve: reserve took 21.15 ms, sched copies = 1
|
|
common_init_from_params: warming up the model with an empty ru
|
|
n - please wait ... (--no-warmup to disable)
|
|
srv load_model: initializing slots, n_slots = 1
|
|
common_speculative_is_compat: the target context does not supp
|
|
ort partial sequence removal
|
|
srv load_model: speculative decoding not supported by this
|
|
context
|
|
slot load_model: id 0 | task -1 | new slot, n_ctx = 32768
|
|
srv load_model: prompt cache is enabled, size limit: 8192 M
|
|
iB
|
|
srv load_model: use `--cache-ram 0` to disable the prompt c
|
|
ache
|
|
srv load_model: for more info see https://github.com/ggml-o
|
|
rg/llama.cpp/pull/16391
|
|
srv init: init: --clear-idle requires --kv-unified, d
|
|
isabling
|
|
init: chat template, 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
|
|
<think>
|
|
'
|
|
srv init: init: chat template, thinking = 1
|
|
main: model loaded
|
|
main: server is listening on http://0.0.0.0:8000
|
|
main: starting the main loop...
|
|
srv update_slots: all slots are idle
|
|
srv params_from_: Chat format: peg-native
|
|
slot get_availabl: id 0 | task -1 | selected slot by LRU, t_l
|
|
ast = -1
|
|
srv get_availabl: updating prompt cache
|
|
srv load: - looking for better prompt, base f_keep =
|
|
-1.000, sim = 0.000
|
|
srv update: - cache state: 0 prompts, 0.000 MiB (limit
|
|
s: 8192.000 MiB, 32768 tokens, 8589934592 est)
|
|
srv get_availabl: prompt cache update took 0.14 ms
|
|
slot launch_slot_: id 0 | task -1 | sampler chain: logits ->
|
|
?penalties -> ?dry -> ?top-n-sigma -> top-k -> ?typical -> top
|
|
-p -> min-p -> ?xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 0 | task 0 | processing task, is_child
|
|
= 0
|
|
slot update_slots: id 0 | task 0 | new prompt, n_ctx_slot = 3
|
|
2768, n_keep = 0, task.n_tokens = 18
|
|
slot update_slots: id 0 | task 0 | n_tokens = 0, memory_seq_r
|
|
m [0, end)
|
|
slot update_slots: id 0 | task 0 | prompt processing progress
|
|
, n_tokens = 14, batch.n_tokens = 14, progress = 0.777778
|
|
slot update_slots: id 0 | task 0 | n_tokens = 14, memory_seq_
|
|
rm [14, end)
|
|
reasoning-budget: activated, budget=2147483647 tokens
|
|
slot init_sampler: id 0 | task 0 | init sampler, took 0.01 ms
|
|
, tokens: text = 18, total = 18
|
|
slot update_slots: id 0 | task 0 | prompt processing done, n_
|
|
tokens = 18, batch.n_tokens = 4
|
|
slot print_timing: id 0 | task 0 |
|
|
prompt eval time = 1161.28 ms / 18 tokens ( 64.52 ms p
|
|
er token, 15.50 tokens per second)
|
|
eval time = 1530.92 ms / 20 tokens ( 76.55 ms p
|
|
er token, 13.06 tokens per second)
|
|
total time = 2692.20 ms / 38 tokens
|
|
slot release: id 0 | task 0 | stop processing: n_tokens
|
|
= 37, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: done request: POST /v1/chat/completions 127
|
|
.0.0.1 200
|
|
srv params_from_: Chat format: peg-native
|
|
slot get_availabl: id 0 | task -1 | selected slot by LCP simi
|
|
larity, sim_best = 1.000 (> 0.100 thold), f_keep = 0.486
|
|
srv get_availabl: updating prompt cache
|
|
srv prompt_save: - saving prompt with length 37, total stat
|
|
e size = 149.308 MiB
|
|
srv load: - looking for better prompt, base f_keep =
|
|
0.486, sim = 1.000
|
|
srv update: - cache state: 1 prompts, 149.308 MiB (lim
|
|
its: 8192.000 MiB, 32768 tokens, 32768 est)
|
|
srv update: - prompt 000001FA5F5C0330: 37 token
|
|
s, checkpoints: 0, 149.308 MiB
|
|
srv get_availabl: prompt cache update took 48.49 ms
|
|
slot launch_slot_: id 0 | task -1 | sampler chain: logits ->
|
|
?penalties -> ?dry -> ?top-n-sigma -> top-k -> ?typical -> top
|
|
-p -> min-p -> ?xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 0 | task 22 | processing task, is_child
|
|
= 0
|
|
slot update_slots: id 0 | task 22 | new prompt, n_ctx_slot =
|
|
32768, n_keep = 0, task.n_tokens = 18
|
|
slot update_slots: id 0 | task 22 | n_past = 18, slot.prompt.
|
|
tokens.size() = 37, seq_id = 0, pos_min = 36, n_swa = 0
|
|
slot update_slots: id 0 | task 22 | forcing full prompt re-pr
|
|
ocessing due to lack of cache data (likely due to SWA or hybri
|
|
d/recurrent memory, see https://github.com/ggml-org/llama.cpp/
|
|
pull/13194#issuecomment-2868343055)
|
|
slot update_slots: id 0 | task 22 | n_tokens = 0, memory_seq_
|
|
rm [0, end)
|
|
slot update_slots: id 0 | task 22 | prompt processing progres
|
|
s, n_tokens = 14, batch.n_tokens = 14, progress = 0.777778
|
|
slot update_slots: id 0 | task 22 | n_tokens = 14, memory_seq
|
|
_rm [14, end)
|
|
reasoning-budget: activated, budget=2147483647 tokens
|
|
slot init_sampler: id 0 | task 22 | init sampler, took 0.01 m
|
|
s, tokens: text = 18, total = 18
|
|
slot update_slots: id 0 | task 22 | prompt processing done, n
|
|
_tokens = 18, batch.n_tokens = 4
|
|
slot print_timing: id 0 | task 22 |
|
|
prompt eval time = 718.37 ms / 18 tokens ( 39.91 ms p
|
|
er token, 25.06 tokens per second)
|
|
eval time = 29198.37 ms / 200 tokens ( 145.99 ms p
|
|
er token, 6.85 tokens per second)
|
|
total time = 29916.73 ms / 218 tokens
|
|
slot release: id 0 | task 22 | stop processing: n_tokens
|
|
= 217, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: done request: POST /v1/chat/completions 127
|
|
.0.0.1 200
|
|
srv params_from_: Chat format: peg-native
|
|
slot get_availabl: id 0 | task -1 | selected slot by LRU, t_l
|
|
ast = 82476549
|
|
srv get_availabl: updating prompt cache
|
|
srv prompt_save: - saving prompt with length 217, total sta
|
|
te size = 150.498 MiB
|
|
srv alloc: - removing obsolete cached prompt with len
|
|
gth 37
|
|
srv load: - looking for better prompt, base f_keep =
|
|
0.014, sim = 0.008
|
|
srv update: - cache state: 1 prompts, 150.498 MiB (lim
|
|
its: 8192.000 MiB, 32768 tokens, 32768 est)
|
|
srv update: - prompt 000001FA5F5C12F0: 217 token
|
|
s, checkpoints: 0, 150.498 MiB
|
|
srv get_availabl: prompt cache update took 61.27 ms
|
|
slot launch_slot_: id 0 | task -1 | sampler chain: logits ->
|
|
?penalties -> ?dry -> ?top-n-sigma -> top-k -> ?typical -> top
|
|
-p -> min-p -> ?xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 0 | task 224 | processing task, is_chil
|
|
d = 0
|
|
slot update_slots: id 0 | task 224 | new prompt, n_ctx_slot =
|
|
32768, n_keep = 0, task.n_tokens = 394
|
|
slot update_slots: id 0 | task 224 | n_past = 3, slot.prompt.
|
|
tokens.size() = 217, seq_id = 0, pos_min = 216, n_swa = 0
|
|
slot update_slots: id 0 | task 224 | forcing full prompt re-p
|
|
rocessing due to lack of cache data (likely due to SWA or hybr
|
|
id/recurrent memory, see https://github.com/ggml-org/llama.cpp
|
|
/pull/13194#issuecomment-2868343055)
|
|
slot update_slots: id 0 | task 224 | n_tokens = 0, memory_seq
|
|
_rm [0, end)
|
|
slot update_slots: id 0 | task 224 | prompt processing progre
|
|
ss, n_tokens = 390, batch.n_tokens = 390, progress = 0.989848
|
|
slot update_slots: id 0 | task 224 | n_tokens = 390, memory_s
|
|
eq_rm [390, end)
|
|
reasoning-budget: activated, budget=2147483647 tokens
|
|
slot init_sampler: id 0 | task 224 | init sampler, took 0.04
|
|
ms, tokens: text = 394, total = 394
|
|
slot update_slots: id 0 | task 224 | prompt processing done,
|
|
n_tokens = 394, batch.n_tokens = 4
|
|
slot update_slots: id 0 | task 224 | created context checkpoi
|
|
nt 1 of 32 (pos_min = 389, pos_max = 389, n_tokens = 390, size
|
|
= 149.063 MiB)
|
|
slot print_timing: id 0 | task 224 |
|
|
prompt eval time = 9959.99 ms / 394 tokens ( 25.28 ms p
|
|
er token, 39.56 tokens per second)
|
|
eval time = 11503.18 ms / 100 tokens ( 115.03 ms p
|
|
er token, 8.69 tokens per second)
|
|
total time = 21463.17 ms / 494 tokens
|
|
slot release: id 0 | task 224 | stop processing: n_token
|
|
s = 493, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: done request: POST /v1/chat/completions 127
|
|
.0.0.1 200
|
|
srv params_from_: Chat format: peg-native
|
|
slot get_availabl: id 0 | task -1 | selected slot by LRU, t_l
|
|
ast = 104021105
|
|
srv get_availabl: updating prompt cache
|
|
srv prompt_save: - saving prompt with length 493, total sta
|
|
te size = 152.323 MiB
|
|
srv load: - looking for better prompt, base f_keep =
|
|
0.006, sim = 0.001
|
|
srv update: - cache state: 2 prompts, 451.884 MiB (lim
|
|
its: 8192.000 MiB, 32768 tokens, 32768 est)
|
|
srv update: - prompt 000001FA5F5C12F0: 217 token
|
|
s, checkpoints: 0, 150.498 MiB
|
|
srv update: - prompt 000001FA5F5BB400: 493 token
|
|
s, checkpoints: 1, 301.386 MiB
|
|
srv get_availabl: prompt cache update took 82.00 ms
|
|
slot launch_slot_: id 0 | task -1 | sampler chain: logits ->
|
|
?penalties -> ?dry -> ?top-n-sigma -> top-k -> ?typical -> top
|
|
-p -> min-p -> ?xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 0 | task 326 | processing task, is_chil
|
|
d = 0
|
|
slot update_slots: id 0 | task 326 | new prompt, n_ctx_slot =
|
|
32768, n_keep = 0, task.n_tokens = 3223
|
|
slot update_slots: id 0 | task 326 | n_past = 3, slot.prompt.
|
|
tokens.size() = 493, seq_id = 0, pos_min = 492, n_swa = 0
|
|
slot update_slots: id 0 | task 326 | Checking checkpoint with
|
|
[389, 389] against 3...
|
|
slot update_slots: id 0 | task 326 | forcing full prompt re-p
|
|
rocessing due to lack of cache data (likely due to SWA or hybr
|
|
id/recurrent memory, see https://github.com/ggml-org/llama.cpp
|
|
/pull/13194#issuecomment-2868343055)
|
|
slot update_slots: id 0 | task 326 | erased invalidated conte
|
|
xt checkpoint (pos_min = 389, pos_max = 389, n_tokens = 390, n
|
|
_swa = 0, pos_next = 0, size = 149.063 MiB)
|
|
slot update_slots: id 0 | task 326 | n_tokens = 0, memory_seq
|
|
_rm [0, end)
|
|
slot update_slots: id 0 | task 326 | prompt processing progre
|
|
ss, n_tokens = 2048, batch.n_tokens = 2048, progress = 0.63543
|
|
3
|
|
slot update_slots: id 0 | task 326 | n_tokens = 2048, memory_
|
|
seq_rm [2048, end)
|
|
slot update_slots: id 0 | task 326 | prompt processing progre
|
|
ss, n_tokens = 2707, batch.n_tokens = 659, progress = 0.839901
|
|
slot update_slots: id 0 | task 326 | n_tokens = 2707, memory_
|
|
seq_rm [2707, end)
|
|
slot update_slots: id 0 | task 326 | prompt processing progre
|
|
ss, n_tokens = 3219, batch.n_tokens = 512, progress = 0.998759
|
|
slot update_slots: id 0 | task 326 | created context checkpoi
|
|
nt 1 of 32 (pos_min = 2706, pos_max = 2706, n_tokens = 2707, s
|
|
ize = 149.063 MiB)
|
|
slot update_slots: id 0 | task 326 | n_tokens = 3219, memory_
|
|
seq_rm [3219, end)
|
|
reasoning-budget: activated, budget=2147483647 tokens
|
|
slot init_sampler: id 0 | task 326 | init sampler, took 0.32
|
|
ms, tokens: text = 3223, total = 3223
|
|
slot update_slots: id 0 | task 326 | prompt processing done,
|
|
n_tokens = 3223, batch.n_tokens = 4
|
|
slot update_slots: id 0 | task 326 | created context checkpoi
|
|
nt 2 of 32 (pos_min = 3218, pos_max = 3218, n_tokens = 3219, s
|
|
ize = 149.063 MiB)
|
|
slot print_timing: id 0 | task 326 |
|
|
prompt eval time = 92674.85 ms / 3223 tokens ( 28.75 ms p
|
|
er token, 34.78 tokens per second)
|
|
eval time = 11828.92 ms / 100 tokens ( 118.29 ms p
|
|
er token, 8.45 tokens per second)
|
|
total time = 104503.77 ms / 3323 tokens
|
|
slot release: id 0 | task 326 | stop processing: n_token
|
|
s = 3322, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: done request: POST /v1/chat/completions 127
|
|
.0.0.1 200
|
|
srv params_from_: Chat format: peg-native
|
|
slot get_availabl: id 0 | task -1 | selected slot by LCP simi
|
|
larity, sim_best = 0.167 (> 0.100 thold), f_keep = 0.001
|
|
srv get_availabl: updating prompt cache
|
|
srv prompt_save: - saving prompt with length 3322, total st
|
|
ate size = 171.025 MiB
|
|
srv load: - looking for better prompt, base f_keep =
|
|
0.001, sim = 0.167
|
|
srv update: - cache state: 3 prompts, 921.036 MiB (lim
|
|
its: 8192.000 MiB, 32768 tokens, 35861 est)
|
|
srv update: - prompt 000001FA5F5C12F0: 217 token
|
|
s, checkpoints: 0, 150.498 MiB
|
|
srv update: - prompt 000001FA5F5BB400: 493 token
|
|
s, checkpoints: 1, 301.386 MiB
|
|
srv update: - prompt 000002110E94B490: 3322 token
|
|
s, checkpoints: 2, 469.152 MiB
|
|
srv get_availabl: prompt cache update took 130.08 ms
|
|
slot launch_slot_: id 0 | task -1 | sampler chain: logits ->
|
|
?penalties -> ?dry -> ?top-n-sigma -> top-k -> ?typical -> top
|
|
-p -> min-p -> ?xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 0 | task 430 | processing task, is_chil
|
|
d = 0
|
|
slot update_slots: id 0 | task 430 | new prompt, n_ctx_slot =
|
|
32768, n_keep = 0, task.n_tokens = 18
|
|
slot update_slots: id 0 | task 430 | n_past = 3, slot.prompt.
|
|
tokens.size() = 3322, seq_id = 0, pos_min = 3321, n_swa = 0
|
|
slot update_slots: id 0 | task 430 | Checking checkpoint with
|
|
[3218, 3218] against 3...
|
|
slot update_slots: id 0 | task 430 | Checking checkpoint with
|
|
[2706, 2706] against 3...
|
|
slot update_slots: id 0 | task 430 | forcing full prompt re-p
|
|
rocessing due to lack of cache data (likely due to SWA or hybr
|
|
id/recurrent memory, see https://github.com/ggml-org/llama.cpp
|
|
/pull/13194#issuecomment-2868343055)
|
|
slot update_slots: id 0 | task 430 | erased invalidated conte
|
|
xt checkpoint (pos_min = 2706, pos_max = 2706, n_tokens = 2707
|
|
, n_swa = 0, pos_next = 0, size = 149.063 MiB)
|
|
slot update_slots: id 0 | task 430 | erased invalidated conte
|
|
xt checkpoint (pos_min = 3218, pos_max = 3218, n_tokens = 3219
|
|
, n_swa = 0, pos_next = 0, size = 149.063 MiB)
|
|
slot update_slots: id 0 | task 430 | n_tokens = 0, memory_seq
|
|
_rm [0, end)
|
|
slot update_slots: id 0 | task 430 | prompt processing progre
|
|
ss, n_tokens = 14, batch.n_tokens = 14, progress = 0.777778
|
|
slot update_slots: id 0 | task 430 | n_tokens = 14, memory_se
|
|
q_rm [14, end)
|
|
reasoning-budget: activated, budget=2147483647 tokens
|
|
slot init_sampler: id 0 | task 430 | init sampler, took 0.01
|
|
ms, tokens: text = 18, total = 18
|
|
slot update_slots: id 0 | task 430 | prompt processing done,
|
|
n_tokens = 18, batch.n_tokens = 4
|
|
reasoning-budget: deactivated (natural end)
|
|
slot print_timing: id 0 | task 430 |
|
|
prompt eval time = 879.58 ms / 18 tokens ( 48.87 ms p
|
|
er token, 20.46 tokens per second)
|
|
eval time = 50538.29 ms / 361 tokens ( 140.00 ms p
|
|
er token, 7.14 tokens per second)
|
|
total time = 51417.87 ms / 379 tokens
|
|
slot release: id 0 | task 430 | stop processing: n_token
|
|
s = 378, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: done request: POST /v1/chat/completions 127
|
|
.0.0.1 200
|