github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10668] key not found #53525

New Issue
Closed
opened 2026-04-29 03:31:07 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-29 03:31:07 -05:00
Owner
Copy Link

Originally created by @fedesantamarina on GitHub (May 12, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10668

What is the issue?

At the third call from the API it freezes.

Relevant log output

time=2025-05-12T00:22:39.542-03:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
time=2025-05-12T00:22:39.543-03:00 level=WARN source=types.go:570 msg="invalid option provided" option=timeout
time=2025-05-12T00:22:39.557-03:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
time=2025-05-12T00:22:39.569-03:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
time=2025-05-12T00:22:39.570-03:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3moe.vision.block_count default=0
time=2025-05-12T00:22:39.571-03:00 level=INFO source=sched.go:754 msg="new model will fit in available VRAM in single GPU, loading" model=/Users/fede/.ollama/models/blobs/sha256-ae354763fe478c790125fb993e59bb1266655b3fa721eebe4a931660c3ed2ce9 gpu=0 parallel=2 available=77309411328 required="59.4 GiB"
time=2025-05-12T00:22:39.571-03:00 level=INFO source=server.go:106 msg="system memory" total="96.0 GiB" free="47.3 GiB" free_swap="0 B"
time=2025-05-12T00:22:39.571-03:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3moe.vision.block_count default=0
time=2025-05-12T00:22:39.572-03:00 level=INFO source=server.go:139 msg=offload library=metal layers.requested=-1 layers.model=49 layers.offload=49 layers.split="" memory.available="[72.0 GiB]" memory.gpu_overhead="0 B" memory.required.full="59.4 GiB" memory.required.partial="59.4 GiB" memory.required.kv="12.0 GiB" memory.required.allocations="[59.4 GiB]" memory.weights.total="30.0 GiB" memory.weights.repeating="29.7 GiB" memory.weights.nonrepeating="315.3 MiB" memory.graph.full="16.0 GiB" memory.graph.partial="16.0 GiB"
llama_model_load_from_file_impl: using device Metal (Apple M3 Ultra) - 73727 MiB free
llama_model_loader: loaded meta data with 31 key-value pairs and 579 tensors from /Users/fede/.ollama/models/blobs/sha256-ae354763fe478c790125fb993e59bb1266655b3fa721eebe4a931660c3ed2ce9 (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              = qwen3moe
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen3 30B A3B
llama_model_loader: - kv   3:                           general.basename str              = Qwen3
llama_model_loader: - kv   4:                         general.size_label str              = 30B-A3B
llama_model_loader: - kv   5:                            general.license str              = apache-2.0
llama_model_loader: - kv   6:                       qwen3moe.block_count u32              = 48
llama_model_loader: - kv   7:                    qwen3moe.context_length u32              = 40960
llama_model_loader: - kv   8:                  qwen3moe.embedding_length u32              = 2048
llama_model_loader: - kv   9:               qwen3moe.feed_forward_length u32              = 6144
llama_model_loader: - kv  10:              qwen3moe.attention.head_count u32              = 32
llama_model_loader: - kv  11:           qwen3moe.attention.head_count_kv u32              = 4
llama_model_loader: - kv  12:                    qwen3moe.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  13:  qwen3moe.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  14:                 qwen3moe.expert_used_count u32              = 8
llama_model_loader: - kv  15:              qwen3moe.attention.key_length u32              = 128
llama_model_loader: - kv  16:            qwen3moe.attention.value_length u32              = 128
llama_model_loader: - kv  17:                      qwen3moe.expert_count u32              = 128
llama_model_loader: - kv  18:        qwen3moe.expert_feed_forward_length u32              = 768
llama_model_loader: - kv  19:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  20:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  21:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  22:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  23:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  24:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  25:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  26:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  27:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  29:               general.quantization_version u32              = 2
llama_model_loader: - kv  30:                          general.file_type u32              = 7
llama_model_loader: - type  f32:  241 tensors
llama_model_loader: - type  f16:   48 tensors
llama_model_loader: - type q8_0:  290 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q8_0
print_info: file size   = 30.29 GiB (8.52 BPW)
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch             = qwen3moe
print_info: vocab_only       = 1
print_info: model type       = ?B
print_info: model params     = 30.53 B
print_info: general.name     = Qwen3 30B A3B
print_info: n_ff_exp         = 0
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
llama_model_load: vocab only - skipping tensors
time=2025-05-12T00:22:39.686-03:00 level=INFO source=server.go:410 msg="starting llama server" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --model /Users/fede/.ollama/models/blobs/sha256-ae354763fe478c790125fb993e59bb1266655b3fa721eebe4a931660c3ed2ce9 --ctx-size 131072 --batch-size 512 --n-gpu-layers 49 --threads 20 --parallel 2 --port 63646"
time=2025-05-12T00:22:39.690-03:00 level=INFO source=sched.go:452 msg="loaded runners" count=1
time=2025-05-12T00:22:39.690-03:00 level=INFO source=server.go:589 msg="waiting for llama runner to start responding"
time=2025-05-12T00:22:39.690-03:00 level=INFO source=server.go:623 msg="waiting for server to become available" status="llm server not responding"
time=2025-05-12T00:22:39.697-03:00 level=INFO source=runner.go:853 msg="starting go runner"
time=2025-05-12T00:22:39.700-03:00 level=INFO source=ggml.go:103 msg=system Metal.0.EMBED_LIBRARY=1 CPU.0.ARM_FMA=1 CPU.0.FP16_VA=1 CPU.0.DOTPROD=1 CPU.0.LLAMAFILE=1 CPU.0.ACCELERATE=1 compiler=cgo(clang)
time=2025-05-12T00:22:39.700-03:00 level=INFO source=runner.go:913 msg="Server listening on 127.0.0.1:63646"
llama_model_load_from_file_impl: using device Metal (Apple M3 Ultra) - 73727 MiB free
llama_model_loader: loaded meta data with 31 key-value pairs and 579 tensors from /Users/fede/.ollama/models/blobs/sha256-ae354763fe478c790125fb993e59bb1266655b3fa721eebe4a931660c3ed2ce9 (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              = qwen3moe
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen3 30B A3B
llama_model_loader: - kv   3:                           general.basename str              = Qwen3
llama_model_loader: - kv   4:                         general.size_label str              = 30B-A3B
llama_model_loader: - kv   5:                            general.license str              = apache-2.0
llama_model_loader: - kv   6:                       qwen3moe.block_count u32              = 48
llama_model_loader: - kv   7:                    qwen3moe.context_length u32              = 40960
llama_model_loader: - kv   8:                  qwen3moe.embedding_length u32              = 2048
llama_model_loader: - kv   9:               qwen3moe.feed_forward_length u32              = 6144
llama_model_loader: - kv  10:              qwen3moe.attention.head_count u32              = 32
llama_model_loader: - kv  11:           qwen3moe.attention.head_count_kv u32              = 4
llama_model_loader: - kv  12:                    qwen3moe.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  13:  qwen3moe.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  14:                 qwen3moe.expert_used_count u32              = 8
llama_model_loader: - kv  15:              qwen3moe.attention.key_length u32              = 128
llama_model_loader: - kv  16:            qwen3moe.attention.value_length u32              = 128
llama_model_loader: - kv  17:                      qwen3moe.expert_count u32              = 128
llama_model_loader: - kv  18:        qwen3moe.expert_feed_forward_length u32              = 768
llama_model_loader: - kv  19:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  20:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  21:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  22:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  23:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  24:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  25:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  26:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  27:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  29:               general.quantization_version u32              = 2
llama_model_loader: - kv  30:                          general.file_type u32              = 7
llama_model_loader: - type  f32:  241 tensors
llama_model_loader: - type  f16:   48 tensors
llama_model_loader: - type q8_0:  290 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q8_0
print_info: file size   = 30.29 GiB (8.52 BPW)
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch             = qwen3moe
print_info: vocab_only       = 0
print_info: n_ctx_train      = 40960
print_info: n_embd           = 2048
print_info: n_layer          = 48
print_info: n_head           = 32
print_info: n_head_kv        = 4
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: n_swa_pattern    = 1
print_info: n_embd_head_k    = 128
print_info: n_embd_head_v    = 128
print_info: n_gqa            = 8
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             = 6144
print_info: n_expert         = 128
print_info: n_expert_used    = 8
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  = 40960
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       = 30B.A3B
print_info: model params     = 30.53 B
print_info: general.name     = Qwen3 30B A3B
print_info: n_ff_exp         = 768
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)
time=2025-05-12T00:22:39.942-03:00 level=INFO source=server.go:623 msg="waiting for server to become available" status="llm server loading model"
load_tensors: offloading 48 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 49/49 layers to GPU
load_tensors:   CPU_Mapped model buffer size =   315.30 MiB
load_tensors: Metal_Mapped model buffer size = 31018.40 MiB
llama_context: constructing llama_context
llama_context: n_seq_max     = 2
llama_context: n_ctx         = 131072
llama_context: n_ctx_per_seq = 65536
llama_context: n_batch       = 1024
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 1
llama_context: flash_attn    = 0
llama_context: freq_base     = 1000000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_per_seq (65536) > n_ctx_train (40960) -- possible training context overflow
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M3 Ultra
ggml_metal_init: picking default device: Apple M3 Ultra
ggml_metal_load_library: using embedded metal library
ggml_metal_init: GPU name:   Apple M3 Ultra
ggml_metal_init: GPU family: MTLGPUFamilyApple9  (1009)
ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_init: GPU family: MTLGPUFamilyMetal3  (5001)
ggml_metal_init: simdgroup reduction   = true
ggml_metal_init: simdgroup matrix mul. = true
ggml_metal_init: has residency sets    = false
ggml_metal_init: has bfloat            = true
ggml_metal_init: use bfloat            = false
ggml_metal_init: hasUnifiedMemory      = true
ggml_metal_init: recommendedMaxWorkingSetSize  = 77309.41 MB
ggml_metal_init: skipping kernel_get_rows_bf16                     (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32                   (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32_1row              (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32_l4                (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_bf16                  (not supported)
ggml_metal_init: skipping kernel_mul_mv_id_bf16_f32                (not supported)
ggml_metal_init: skipping kernel_mul_mm_bf16_f32                   (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_bf16_f32                (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h64           (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h80           (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h96           (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h112          (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h128          (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h192          (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_hk192_hv128   (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h256          (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_hk576_hv512   (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h96       (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h128      (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h192      (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_hk192_hv128 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h256      (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_hk576_hv512 (not supported)
ggml_metal_init: skipping kernel_cpy_f32_bf16                      (not supported)
ggml_metal_init: skipping kernel_cpy_bf16_f32                      (not supported)
ggml_metal_init: skipping kernel_cpy_bf16_bf16                     (not supported)
llama_context:        CPU  output buffer size =     1.17 MiB
init: kv_size = 131072, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 48, can_shift = 1
init:      Metal KV buffer size = 12288.00 MiB
llama_context: KV self size  = 12288.00 MiB, K (f16): 6144.00 MiB, V (f16): 6144.00 MiB
llama_context:      Metal compute buffer size =  8472.00 MiB
llama_context:        CPU compute buffer size =   260.01 MiB
llama_context: graph nodes  = 3126
llama_context: graph splits = 2
time=2025-05-12T00:22:42.205-03:00 level=INFO source=server.go:628 msg="llama runner started in 2.51 seconds"
[GIN] 2025/05/12 - 00:22:54 | 500 | 14.649193709s |       127.0.0.1 | POST     "/api/chat"
time=2025-05-12T00:23:05.643-03:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
time=2025-05-12T00:23:05.644-03:00 level=WARN source=types.go:570 msg="invalid option provided" option=timeout
[GIN] 2025/05/12 - 00:24:09 | 200 |          1m3s |       127.0.0.1 | POST     "/api/chat"
time=2025-05-12T00:24:15.504-03:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
time=2025-05-12T00:24:15.505-03:00 level=WARN source=types.go:570 msg="invalid option provided" option=timeout
[GIN] 2025/05/12 - 00:24:44 | 200 | 29.365388833s |       127.0.0.1 | POST     "/api/chat"
time=2025-05-12T00:24:50.452-03:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
time=2025-05-12T00:24:50.453-03:00 level=WARN source=types.go:570 msg="invalid option provided" option=timeout
[GIN] 2025/05/12 - 00:27:53 | 200 |          17µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/05/12 - 00:27:53 | 200 |      20.375µs |       127.0.0.1 | GET      "/api/ps"

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @fedesantamarina on GitHub (May 12, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10668 ### What is the issue? At the third call from the API it freezes. ### Relevant log output ```shell time=2025-05-12T00:22:39.542-03:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 time=2025-05-12T00:22:39.543-03:00 level=WARN source=types.go:570 msg="invalid option provided" option=timeout time=2025-05-12T00:22:39.557-03:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 time=2025-05-12T00:22:39.569-03:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 time=2025-05-12T00:22:39.570-03:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3moe.vision.block_count default=0 time=2025-05-12T00:22:39.571-03:00 level=INFO source=sched.go:754 msg="new model will fit in available VRAM in single GPU, loading" model=/Users/fede/.ollama/models/blobs/sha256-ae354763fe478c790125fb993e59bb1266655b3fa721eebe4a931660c3ed2ce9 gpu=0 parallel=2 available=77309411328 required="59.4 GiB" time=2025-05-12T00:22:39.571-03:00 level=INFO source=server.go:106 msg="system memory" total="96.0 GiB" free="47.3 GiB" free_swap="0 B" time=2025-05-12T00:22:39.571-03:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3moe.vision.block_count default=0 time=2025-05-12T00:22:39.572-03:00 level=INFO source=server.go:139 msg=offload library=metal layers.requested=-1 layers.model=49 layers.offload=49 layers.split="" memory.available="[72.0 GiB]" memory.gpu_overhead="0 B" memory.required.full="59.4 GiB" memory.required.partial="59.4 GiB" memory.required.kv="12.0 GiB" memory.required.allocations="[59.4 GiB]" memory.weights.total="30.0 GiB" memory.weights.repeating="29.7 GiB" memory.weights.nonrepeating="315.3 MiB" memory.graph.full="16.0 GiB" memory.graph.partial="16.0 GiB" llama_model_load_from_file_impl: using device Metal (Apple M3 Ultra) - 73727 MiB free llama_model_loader: loaded meta data with 31 key-value pairs and 579 tensors from /Users/fede/.ollama/models/blobs/sha256-ae354763fe478c790125fb993e59bb1266655b3fa721eebe4a931660c3ed2ce9 (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 = qwen3moe llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Qwen3 30B A3B llama_model_loader: - kv 3: general.basename str = Qwen3 llama_model_loader: - kv 4: general.size_label str = 30B-A3B llama_model_loader: - kv 5: general.license str = apache-2.0 llama_model_loader: - kv 6: qwen3moe.block_count u32 = 48 llama_model_loader: - kv 7: qwen3moe.context_length u32 = 40960 llama_model_loader: - kv 8: qwen3moe.embedding_length u32 = 2048 llama_model_loader: - kv 9: qwen3moe.feed_forward_length u32 = 6144 llama_model_loader: - kv 10: qwen3moe.attention.head_count u32 = 32 llama_model_loader: - kv 11: qwen3moe.attention.head_count_kv u32 = 4 llama_model_loader: - kv 12: qwen3moe.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 13: qwen3moe.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 14: qwen3moe.expert_used_count u32 = 8 llama_model_loader: - kv 15: qwen3moe.attention.key_length u32 = 128 llama_model_loader: - kv 16: qwen3moe.attention.value_length u32 = 128 llama_model_loader: - kv 17: qwen3moe.expert_count u32 = 128 llama_model_loader: - kv 18: qwen3moe.expert_feed_forward_length u32 = 768 llama_model_loader: - kv 19: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 20: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 21: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 22: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 23: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 25: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 26: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 27: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 28: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 29: general.quantization_version u32 = 2 llama_model_loader: - kv 30: general.file_type u32 = 7 llama_model_loader: - type f32: 241 tensors llama_model_loader: - type f16: 48 tensors llama_model_loader: - type q8_0: 290 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q8_0 print_info: file size = 30.29 GiB (8.52 BPW) load: special tokens cache size = 26 load: token to piece cache size = 0.9311 MB print_info: arch = qwen3moe print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 30.53 B print_info: general.name = Qwen3 30B A3B print_info: n_ff_exp = 0 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 llama_model_load: vocab only - skipping tensors time=2025-05-12T00:22:39.686-03:00 level=INFO source=server.go:410 msg="starting llama server" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --model /Users/fede/.ollama/models/blobs/sha256-ae354763fe478c790125fb993e59bb1266655b3fa721eebe4a931660c3ed2ce9 --ctx-size 131072 --batch-size 512 --n-gpu-layers 49 --threads 20 --parallel 2 --port 63646" time=2025-05-12T00:22:39.690-03:00 level=INFO source=sched.go:452 msg="loaded runners" count=1 time=2025-05-12T00:22:39.690-03:00 level=INFO source=server.go:589 msg="waiting for llama runner to start responding" time=2025-05-12T00:22:39.690-03:00 level=INFO source=server.go:623 msg="waiting for server to become available" status="llm server not responding" time=2025-05-12T00:22:39.697-03:00 level=INFO source=runner.go:853 msg="starting go runner" time=2025-05-12T00:22:39.700-03:00 level=INFO source=ggml.go:103 msg=system Metal.0.EMBED_LIBRARY=1 CPU.0.ARM_FMA=1 CPU.0.FP16_VA=1 CPU.0.DOTPROD=1 CPU.0.LLAMAFILE=1 CPU.0.ACCELERATE=1 compiler=cgo(clang) time=2025-05-12T00:22:39.700-03:00 level=INFO source=runner.go:913 msg="Server listening on 127.0.0.1:63646" llama_model_load_from_file_impl: using device Metal (Apple M3 Ultra) - 73727 MiB free llama_model_loader: loaded meta data with 31 key-value pairs and 579 tensors from /Users/fede/.ollama/models/blobs/sha256-ae354763fe478c790125fb993e59bb1266655b3fa721eebe4a931660c3ed2ce9 (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 = qwen3moe llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Qwen3 30B A3B llama_model_loader: - kv 3: general.basename str = Qwen3 llama_model_loader: - kv 4: general.size_label str = 30B-A3B llama_model_loader: - kv 5: general.license str = apache-2.0 llama_model_loader: - kv 6: qwen3moe.block_count u32 = 48 llama_model_loader: - kv 7: qwen3moe.context_length u32 = 40960 llama_model_loader: - kv 8: qwen3moe.embedding_length u32 = 2048 llama_model_loader: - kv 9: qwen3moe.feed_forward_length u32 = 6144 llama_model_loader: - kv 10: qwen3moe.attention.head_count u32 = 32 llama_model_loader: - kv 11: qwen3moe.attention.head_count_kv u32 = 4 llama_model_loader: - kv 12: qwen3moe.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 13: qwen3moe.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 14: qwen3moe.expert_used_count u32 = 8 llama_model_loader: - kv 15: qwen3moe.attention.key_length u32 = 128 llama_model_loader: - kv 16: qwen3moe.attention.value_length u32 = 128 llama_model_loader: - kv 17: qwen3moe.expert_count u32 = 128 llama_model_loader: - kv 18: qwen3moe.expert_feed_forward_length u32 = 768 llama_model_loader: - kv 19: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 20: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 21: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 22: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 23: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 25: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 26: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 27: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 28: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 29: general.quantization_version u32 = 2 llama_model_loader: - kv 30: general.file_type u32 = 7 llama_model_loader: - type f32: 241 tensors llama_model_loader: - type f16: 48 tensors llama_model_loader: - type q8_0: 290 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q8_0 print_info: file size = 30.29 GiB (8.52 BPW) load: special tokens cache size = 26 load: token to piece cache size = 0.9311 MB print_info: arch = qwen3moe print_info: vocab_only = 0 print_info: n_ctx_train = 40960 print_info: n_embd = 2048 print_info: n_layer = 48 print_info: n_head = 32 print_info: n_head_kv = 4 print_info: n_rot = 128 print_info: n_swa = 0 print_info: n_swa_pattern = 1 print_info: n_embd_head_k = 128 print_info: n_embd_head_v = 128 print_info: n_gqa = 8 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 = 6144 print_info: n_expert = 128 print_info: n_expert_used = 8 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 = 40960 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 = 30B.A3B print_info: model params = 30.53 B print_info: general.name = Qwen3 30B A3B print_info: n_ff_exp = 768 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) time=2025-05-12T00:22:39.942-03:00 level=INFO source=server.go:623 msg="waiting for server to become available" status="llm server loading model" load_tensors: offloading 48 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 49/49 layers to GPU load_tensors: CPU_Mapped model buffer size = 315.30 MiB load_tensors: Metal_Mapped model buffer size = 31018.40 MiB llama_context: constructing llama_context llama_context: n_seq_max = 2 llama_context: n_ctx = 131072 llama_context: n_ctx_per_seq = 65536 llama_context: n_batch = 1024 llama_context: n_ubatch = 512 llama_context: causal_attn = 1 llama_context: flash_attn = 0 llama_context: freq_base = 1000000.0 llama_context: freq_scale = 1 llama_context: n_ctx_per_seq (65536) > n_ctx_train (40960) -- possible training context overflow ggml_metal_init: allocating ggml_metal_init: found device: Apple M3 Ultra ggml_metal_init: picking default device: Apple M3 Ultra ggml_metal_load_library: using embedded metal library ggml_metal_init: GPU name: Apple M3 Ultra ggml_metal_init: GPU family: MTLGPUFamilyApple9 (1009) ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003) ggml_metal_init: GPU family: MTLGPUFamilyMetal3 (5001) ggml_metal_init: simdgroup reduction = true ggml_metal_init: simdgroup matrix mul. = true ggml_metal_init: has residency sets = false ggml_metal_init: has bfloat = true ggml_metal_init: use bfloat = false ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: recommendedMaxWorkingSetSize = 77309.41 MB ggml_metal_init: skipping kernel_get_rows_bf16 (not supported) ggml_metal_init: skipping kernel_mul_mv_bf16_f32 (not supported) ggml_metal_init: skipping kernel_mul_mv_bf16_f32_1row (not supported) ggml_metal_init: skipping kernel_mul_mv_bf16_f32_l4 (not supported) ggml_metal_init: skipping kernel_mul_mv_bf16_bf16 (not supported) ggml_metal_init: skipping kernel_mul_mv_id_bf16_f32 (not supported) ggml_metal_init: skipping kernel_mul_mm_bf16_f32 (not supported) ggml_metal_init: skipping kernel_mul_mm_id_bf16_f32 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h64 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h80 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h96 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h112 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h128 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h192 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_bf16_hk192_hv128 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h256 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_bf16_hk576_hv512 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h96 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h128 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h192 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_hk192_hv128 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h256 (not supported) ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_hk576_hv512 (not supported) ggml_metal_init: skipping kernel_cpy_f32_bf16 (not supported) ggml_metal_init: skipping kernel_cpy_bf16_f32 (not supported) ggml_metal_init: skipping kernel_cpy_bf16_bf16 (not supported) llama_context: CPU output buffer size = 1.17 MiB init: kv_size = 131072, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 48, can_shift = 1 init: Metal KV buffer size = 12288.00 MiB llama_context: KV self size = 12288.00 MiB, K (f16): 6144.00 MiB, V (f16): 6144.00 MiB llama_context: Metal compute buffer size = 8472.00 MiB llama_context: CPU compute buffer size = 260.01 MiB llama_context: graph nodes = 3126 llama_context: graph splits = 2 time=2025-05-12T00:22:42.205-03:00 level=INFO source=server.go:628 msg="llama runner started in 2.51 seconds" [GIN] 2025/05/12 - 00:22:54 | 500 | 14.649193709s | 127.0.0.1 | POST "/api/chat" time=2025-05-12T00:23:05.643-03:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 time=2025-05-12T00:23:05.644-03:00 level=WARN source=types.go:570 msg="invalid option provided" option=timeout [GIN] 2025/05/12 - 00:24:09 | 200 | 1m3s | 127.0.0.1 | POST "/api/chat" time=2025-05-12T00:24:15.504-03:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 time=2025-05-12T00:24:15.505-03:00 level=WARN source=types.go:570 msg="invalid option provided" option=timeout [GIN] 2025/05/12 - 00:24:44 | 200 | 29.365388833s | 127.0.0.1 | POST "/api/chat" time=2025-05-12T00:24:50.452-03:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 time=2025-05-12T00:24:50.453-03:00 level=WARN source=types.go:570 msg="invalid option provided" option=timeout [GIN] 2025/05/12 - 00:27:53 | 200 | 17µs | 127.0.0.1 | HEAD "/" [GIN] 2025/05/12 - 00:27:53 | 200 | 20.375µs | 127.0.0.1 | GET "/api/ps" ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-29 03:31:07 -05:00
GiteaMirror commented 2026-04-29 03:31:13 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 12, 2025):

key not found is just a warning and doesn't indicate anything wrong. Can you give more details about what you are experiencing? Setting OLLAMA_DEBUG=1 in the server environment will increase logging and may show relevant information.

<!-- gh-comment-id:2871405805 --> @rick-github commented on GitHub (May 12, 2025): `key not found` is just a warning and doesn't indicate anything wrong. Can you give more details about what you are experiencing? Setting `OLLAMA_DEBUG=1` in the server environment will increase logging and may show relevant information.
GiteaMirror commented 2026-04-29 03:31:14 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 12, 2025):

Hi @fedesantamarina the key not found message will be fixed in the next release (thanks @rick-github).

<!-- gh-comment-id:2873130608 --> @jmorganca commented on GitHub (May 12, 2025): Hi @fedesantamarina the `key not found` message will be fixed in the next release (thanks @rick-github).
GiteaMirror commented 2026-04-29 03:31:15 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 12, 2025):

I'm assuming some other problem because of

At the third call from the API it freezes.

<!-- gh-comment-id:2873134808 --> @rick-github commented on GitHub (May 12, 2025): I'm assuming some other problem because of > At the third call from the API it freezes.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#53525
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?