308 lines
28 KiB
Plaintext
308 lines
28 KiB
Plaintext
llama_bin_run\llama-server.exe : ggml_cuda_init: found 1 CU
|
|
DA devices (Total VRAM: 12287 MiB):
|
|
위치 줄:1 문자:1
|
|
+ llama_bin_run\llama-server.exe --model "models\Q4_K_M\Qwe
|
|
n3.5-122B-A1 ...
|
|
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
~~~~~~~~~~~~
|
|
+ CategoryInfo : NotSpecified: (ggml_cuda_ini
|
|
t:...AM: 12287 MiB)::String) [], RemoteException
|
|
+ FullyQualifiedErrorId : NativeCommandError
|
|
|
|
Device 0: NVIDIA GeForce RTX 3060, compute capability 8.6
|
|
, VMM: yes, VRAM: 12287 MiB
|
|
load_backend: loaded CUDA backend from C:\Users\Variet-Work
|
|
er\Desktop\variet-llm\llama_bin_run\ggml-cuda.dll
|
|
load_backend: loaded RPC backend from C:\Users\Variet-Worke
|
|
r\Desktop\variet-llm\llama_bin_run\ggml-rpc.dll
|
|
load_backend: loaded CPU backend from C:\Users\Variet-Worke
|
|
r\Desktop\variet-llm\llama_bin_run\ggml-cpu-haswell.dll
|
|
system info: n_threads = 6, n_threads_batch = 6, total_thre
|
|
ads = 16
|
|
|
|
system_info: n_threads = 6 (n_threads_batch = 6) / 16 | CUD
|
|
A : ARCHS = 500,610,700,750,800,860,890 | USE_GRAPHS = 1 |
|
|
PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AV
|
|
X = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFIL
|
|
E = 1 | OPENMP = 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\Qwen3.5-122
|
|
B-A10B-Q4_K_M-00001-of-00003.gguf'
|
|
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA
|
|
GeForce RTX 3060) (0000:04:00.0) - 11245 MiB free
|
|
llama_model_loader: additional 2 GGUFs metadata loaded.
|
|
llama_model_loader: loaded meta data with 55 key-value pair
|
|
s and 879 tensors from models\Q4_K_M\Qwen3.5-122B-A10B-Q4_K
|
|
_M-00001-of-00003.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 = qwen35moe
|
|
llama_model_loader: - kv 1:
|
|
general.type str = model
|
|
llama_model_loader: - kv 2: general.s
|
|
ampling.top_k i32 = 20
|
|
llama_model_loader: - kv 3: general.s
|
|
ampling.top_p f32 = 0.950000
|
|
llama_model_loader: - kv 4: general.
|
|
sampling.temp f32 = 0.600000
|
|
llama_model_loader: - kv 5:
|
|
general.name str = Qwen3.5-122B-A10B
|
|
llama_model_loader: - kv 6: gen
|
|
eral.basename str = Qwen3.5-122B-A10B
|
|
llama_model_loader: - kv 7: general
|
|
.quantized_by str = Unsloth
|
|
llama_model_loader: - kv 8: gener
|
|
al.size_label str = 122B-A10B
|
|
llama_model_loader: - kv 9: ge
|
|
neral.license str = apache-2.0
|
|
llama_model_loader: - kv 10: general
|
|
.license.link str = https://huggingface.co/Qwe
|
|
n/Qwen3.5-1...
|
|
llama_model_loader: - kv 11: gen
|
|
eral.repo_url str = https://huggingface.co/uns
|
|
loth
|
|
llama_model_loader: - kv 12: general.bas
|
|
e_model.count u32 = 1
|
|
llama_model_loader: - kv 13: general.base
|
|
_model.0.name str = Qwen3.5 122B A10B
|
|
llama_model_loader: - kv 14: general.base_model.0
|
|
.organization str = Qwen
|
|
llama_model_loader: - kv 15: general.base_mod
|
|
el.0.repo_url str = https://huggingface.co/Qwe
|
|
n/Qwen3.5-1...
|
|
llama_model_loader: - kv 16:
|
|
general.tags arr[str,2] = ["unsloth", "image-text-to
|
|
-text"]
|
|
llama_model_loader: - kv 17: qwen35mo
|
|
e.block_count u32 = 48
|
|
llama_model_loader: - kv 18: qwen35moe.c
|
|
ontext_length u32 = 262144
|
|
llama_model_loader: - kv 19: qwen35moe.emb
|
|
edding_length u32 = 3072
|
|
llama_model_loader: - kv 20: qwen35moe.attenti
|
|
on.head_count u32 = 32
|
|
llama_model_loader: - kv 21: qwen35moe.attention.
|
|
head_count_kv u32 = 2
|
|
llama_model_loader: - kv 22: qwen35moe.rope.dimen
|
|
sion_sections arr[i32,4] = [11, 11, 10, 0]
|
|
llama_model_loader: - kv 23: qwen35moe.r
|
|
ope.freq_base f32 = 10000000.000000
|
|
llama_model_loader: - kv 24: qwen35moe.attention.layer_nor
|
|
m_rms_epsilon f32 = 0.000001
|
|
llama_model_loader: - kv 25: qwen35moe
|
|
.expert_count u32 = 256
|
|
llama_model_loader: - kv 26: qwen35moe.expe
|
|
rt_used_count u32 = 8
|
|
llama_model_loader: - kv 27: qwen35moe.attenti
|
|
on.key_length u32 = 256
|
|
llama_model_loader: - kv 28: qwen35moe.attention
|
|
.value_length u32 = 256
|
|
llama_model_loader: - kv 29: qwen35moe.expert_feed_f
|
|
orward_length u32 = 1024
|
|
llama_model_loader: - kv 30: qwen35moe.expert_shared_feed_
|
|
forward_length u32 = 1024
|
|
llama_model_loader: - kv 31: qwen35moe.ss
|
|
m.conv_kernel u32 = 4
|
|
llama_model_loader: - kv 32: qwen35moe.s
|
|
sm.state_size u32 = 128
|
|
llama_model_loader: - kv 33: qwen35moe.ss
|
|
m.group_count u32 = 16
|
|
llama_model_loader: - kv 34: qwen35moe.ssm.t
|
|
ime_step_rank u32 = 64
|
|
llama_model_loader: - kv 35: qwen35moe.s
|
|
sm.inner_size u32 = 8192
|
|
llama_model_loader: - kv 36: qwen35moe.full_atten
|
|
tion_interval u32 = 4
|
|
llama_model_loader: - kv 37: qwen35moe.rope.di
|
|
mension_count u32 = 64
|
|
llama_model_loader: - kv 38: tokeniz
|
|
er.ggml.model str = gpt2
|
|
llama_model_loader: - kv 39: token
|
|
izer.ggml.pre str = qwen35
|
|
llama_model_loader: - kv 40: tokenize
|
|
r.ggml.tokens arr[str,248320] = ["!", "\"", "#", "$", "%",
|
|
"&", "'", ...
|
|
llama_model_loader: - kv 41: tokenizer.gg
|
|
ml.token_type arr[i32,248320] = [1, 1, 1, 1, 1, 1, 1, 1, 1
|
|
, 1, 1, 1, ...
|
|
llama_model_loader: - kv 42: tokenize
|
|
r.ggml.merges arr[str,247587] = ["휔 휔", "휔휔 휔휔", "i n", "휔
|
|
t",...
|
|
llama_model_loader: - kv 43: tokenizer.ggml
|
|
.eos_token_id u32 = 248046
|
|
llama_model_loader: - kv 44: tokenizer.ggml.pad
|
|
ding_token_id u32 = 248055
|
|
llama_model_loader: - kv 45: tokenizer.
|
|
chat_template str = {%- set image_count = name
|
|
space(value...
|
|
llama_model_loader: - kv 46: general.quantiz
|
|
ation_version u32 = 2
|
|
llama_model_loader: - kv 47: gene
|
|
ral.file_type u32 = 15
|
|
llama_model_loader: - kv 48: quantize
|
|
.imatrix.file str = Qwen3.5-122B-A10B-GGUF/ima
|
|
trix_unslot...
|
|
llama_model_loader: - kv 49: quantize.im
|
|
atrix.dataset str = unsloth_calibration_Qwen3.
|
|
5-122B-A10B...
|
|
llama_model_loader: - kv 50: quantize.imatrix.
|
|
entries_count u32 = 612
|
|
llama_model_loader: - kv 51: quantize.imatrix
|
|
.chunks_count u32 = 76
|
|
llama_model_loader: - kv 52:
|
|
split.no u16 = 0
|
|
llama_model_loader: - kv 53: split.
|
|
tensors.count i32 = 879
|
|
llama_model_loader: - kv 54:
|
|
split.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 m
|
|
map enabled - consider using --no-mmap for better performan
|
|
ce
|
|
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 = 4364.17 MiB
|
|
load_tensors: CUDA0 model buffer size = 24879.88 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 = 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 = enabled
|
|
llama_context: kv_unified = false
|
|
llama_context: freq_base = 10000000.0
|
|
llama_context: freq_scale = 1
|
|
llama_context: n_ctx_seq (8192) < n_ctx_train (262144) -- t
|
|
he full capacity of the model will not be utilized
|
|
llama_context: CUDA_Host output buffer size = 0.95 Mi
|
|
B
|
|
llama_kv_cache: CUDA0 KV buffer size = 54.00 MiB
|
|
llama_kv_cache: size = 54.00 MiB ( 8192 cells, 12 layer
|
|
s, 1/1 seqs), K (q4_0): 27.00 MiB, V (q4_0): 27.00 MiB
|
|
llama_kv_cache: attn_rot_k = 1
|
|
llama_kv_cache: attn_rot_v = 1
|
|
llama_memory_recurrent: CUDA0 RS buffer size = 149.0
|
|
6 MiB
|
|
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) enabl
|
|
ed
|
|
sched_reserve: fused Gated Delta Net (chunked) enabled
|
|
sched_reserve: CUDA0 compute buffer size = 650.30 Mi
|
|
B
|
|
sched_reserve: CUDA_Host compute buffer size = 28.29 Mi
|
|
B
|
|
sched_reserve: graph nodes = 4617
|
|
sched_reserve: graph splits = 104 (with bs=512), 70 (with b
|
|
s=1)
|
|
sched_reserve: reserve took 30.84 ms, sched copies = 1
|
|
common_init_from_params: warming up the model with an empty
|
|
run - please wait ... (--no-warmup to disable)
|
|
srv load_model: initializing slots, n_slots = 1
|
|
common_speculative_is_compat: the target context does not s
|
|
upport partial sequence removal
|