github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-21 13:11:39 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #5998] "Error loading llama server" when using a T5ForConditionalGeneration architucture model, converted to GGUF format #50262

New Issue
Open
opened 2026-04-28 14:53:06 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-28 14:53:06 -05:00
Owner
Copy Link

Originally created by @iG8R on GitHub (Jul 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5998

What is the issue?

With the help of https://huggingface.co/spaces/ggml-org/gguf-my-repo I made the https://huggingface.co/iG8R/t5_translate_en_ru_zh_large_1024_v2-Q8_0-GGUF model which was successfully imported into ollama.
But when I try to use it, I always get the following error, while all other models work almost perfectly:

GGML_ASSERT: C:\a\ollama\ollama\llm\llama.cpp\src\llama.cpp:14882: strcmp(embd->name, "result_norm") == 0
time=2024-07-26T23:33:10.669+03:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error"
time=2024-07-26T23:33:10.934+03:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409"
[GIN] 2024/07/26 - 23:33:10 | 500 |    9.3372066s |       127.0.0.1 | POST     "/v1/chat/completions"

Here is the full log:

time=2024-07-26T23:33:09.450+03:00 level=WARN source=memory.go:115 msg="model missing blk.0 layer size"
time=2024-07-26T23:33:09.451+03:00 level=INFO source=sched.go:701 msg="new model will fit in available VRAM in single GPU, loading" model=H:\OllamaModels\blobs\sha256-cca50b43a8d0071238d9cb22864768dec5a8146f0b9969b83e69a076e267b17e gpu=GPU-60a344b3-0290-00b9-ed05-6b799407d228 parallel=4 available=10883338240 required="702.5 MiB"
time=2024-07-26T23:33:09.451+03:00 level=WARN source=memory.go:115 msg="model missing blk.0 layer size"
time=2024-07-26T23:33:09.451+03:00 level=INFO source=memory.go:309 msg="offload to cuda" layers.requested=-1 layers.model=25 layers.offload=25 layers.split="" memory.available="[10.1 GiB]" memory.required.full="702.5 MiB" memory.required.partial="702.5 MiB" memory.required.kv="48.0 MiB" memory.required.allocations="[702.5 MiB]" memory.weights.total="48.0 MiB" memory.weights.repeating="17179869184.0 GiB" memory.weights.nonrepeating="67.5 MiB" memory.graph.full="128.0 MiB" memory.graph.partial="128.0 MiB"
time=2024-07-26T23:33:09.455+03:00 level=INFO source=server.go:383 msg="starting llama server" cmd="f:\\Ollama\\ollama_runners\\cuda_v11.3\\ollama_llama_server.exe --model H:\\OllamaModels\\blobs\\sha256-cca50b43a8d0071238d9cb22864768dec5a8146f0b9969b83e69a076e267b17e --ctx-size 8192 --batch-size 512 --embedding --log-disable --n-gpu-layers 25 --no-mmap --parallel 4 --port 62423"
time=2024-07-26T23:33:09.459+03:00 level=INFO source=sched.go:437 msg="loaded runners" count=1
time=2024-07-26T23:33:09.459+03:00 level=INFO source=server.go:583 msg="waiting for llama runner to start responding"
time=2024-07-26T23:33:09.461+03:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error"
INFO [wmain] build info | build=3440 commit="d94c6e0c" tid="17472" timestamp=1722025989
INFO [wmain] system info | n_threads=4 n_threads_batch=-1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 0 | " tid="17472" timestamp=1722025989 total_threads=8
INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="7" port="62423" tid="17472" timestamp=1722025989
llama_model_loader: loaded meta data with 33 key-value pairs and 558 tensors from H:\OllamaModels\blobs\sha256-cca50b43a8d0071238d9cb22864768dec5a8146f0b9969b83e69a076e267b17e (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              = t5
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = T5_Translate_En_Ru_Zh_Large_1024_V2
llama_model_loader: - kv   3:                         general.size_label str              = 851M
llama_model_loader: - kv   4:                            general.license str              = apache-2.0
llama_model_loader: - kv   5:                               general.tags arr[str,1]       = ["translation"]
llama_model_loader: - kv   6:                          general.languages arr[str,3]       = ["ru", "zh", "en"]
llama_model_loader: - kv   7:                           general.datasets arr[str,1]       = ["ccmatrix"]
llama_model_loader: - kv   8:                          t5.context_length u32              = 512
llama_model_loader: - kv   9:                        t5.embedding_length u32              = 1024
llama_model_loader: - kv  10:                     t5.feed_forward_length u32              = 2816
llama_model_loader: - kv  11:                             t5.block_count u32              = 24
llama_model_loader: - kv  12:                    t5.attention.head_count u32              = 16
llama_model_loader: - kv  13:                    t5.attention.key_length u32              = 64
llama_model_loader: - kv  14:                  t5.attention.value_length u32              = 64
llama_model_loader: - kv  15:            t5.attention.layer_norm_epsilon f32              = 0.000001
llama_model_loader: - kv  16:        t5.attention.relative_buckets_count u32              = 32
llama_model_loader: - kv  17:        t5.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  18:                  t5.decoder_start_token_id u32              = 0
llama_model_loader: - kv  19:                          general.file_type u32              = 7
llama_model_loader: - kv  20:                       tokenizer.ggml.model str              = t5
llama_model_loader: - kv  21:                         tokenizer.ggml.pre str              = default
llama_model_loader: - kv  22:                      tokenizer.ggml.tokens arr[str,65100]   = ["<pad>", "</s>", "<unk>", ",", "▁"...
llama_model_loader: - kv  23:                      tokenizer.ggml.scores arr[f32,65100]   = [0.000000, 0.000000, 0.000000, -3.144...
llama_model_loader: - kv  24:                  tokenizer.ggml.token_type arr[i32,65100]   = [3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  25:            tokenizer.ggml.add_space_prefix bool             = true
llama_model_loader: - kv  26:    tokenizer.ggml.remove_extra_whitespaces bool             = true
llama_model_loader: - kv  27:        tokenizer.ggml.precompiled_charsmap arr[u8,237561]   = [0, 180, 2, 0, 0, 132, 0, 0, 0, 0, 0,...
llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 1
llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 0
llama_model_loader: - kv  30:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  31:               tokenizer.ggml.add_eos_token bool             = true
llama_model_loader: - kv  32:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  122 tensors
llama_model_loader: - type  f16:    2 tensors
llama_model_loader: - type q8_0:  434 tensors
time=2024-07-26T23:33:09.722+03:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server loading model"
llm_load_vocab: special tokens cache size = 103
llm_load_vocab: token to piece cache size = 0.5577 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = t5
llm_load_print_meta: vocab type       = UGM
llm_load_print_meta: n_vocab          = 65100
llm_load_print_meta: n_merges         = 0
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 512
llm_load_print_meta: n_embd           = 1024
llm_load_print_meta: n_layer          = 24
llm_load_print_meta: n_head           = 16
llm_load_print_meta: n_head_kv        = 16
llm_load_print_meta: n_rot            = 64
llm_load_print_meta: n_swa            = 0
llm_load_print_meta: n_embd_head_k    = 64
llm_load_print_meta: n_embd_head_v    = 64
llm_load_print_meta: n_gqa            = 1
llm_load_print_meta: n_embd_k_gqa     = 1024
llm_load_print_meta: n_embd_v_gqa     = 1024
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-06
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 2816
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = -1
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 512
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: model type       = 780M
llm_load_print_meta: model ftype      = Q8_0
llm_load_print_meta: model params     = 850.68 M
llm_load_print_meta: model size       = 862.32 MiB (8.50 BPW)
llm_load_print_meta: general.name     = T5_Translate_En_Ru_Zh_Large_1024_V2
llm_load_print_meta: EOS token        = 1 '</s>'
llm_load_print_meta: UNK token        = 2 '<unk>'
llm_load_print_meta: PAD token        = 0 '<pad>'
llm_load_print_meta: LF token         = 4 '▁'
llm_load_print_meta: max token length = 48
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 3080 Ti, compute capability 8.6, VMM: yes
llm_load_tensors: ggml ctx size =    0.44 MiB
llm_load_tensors: offloading 24 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 25/25 layers to GPU
llm_load_tensors:  CUDA_Host buffer size =    67.55 MiB
llm_load_tensors:      CUDA0 buffer size =   794.79 MiB
llama_new_context_with_model: n_ctx      = 8192
llama_new_context_with_model: n_batch    = 512
llama_new_context_with_model: n_ubatch   = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base  = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init:      CUDA0 KV buffer size =   768.00 MiB
llama_new_context_with_model: KV self size  =  768.00 MiB, K (f16):  384.00 MiB, V (f16):  384.00 MiB
llama_new_context_with_model:  CUDA_Host  output buffer size =     1.01 MiB
llama_new_context_with_model:      CUDA0 compute buffer size =  1046.00 MiB
llama_new_context_with_model:  CUDA_Host compute buffer size =   291.00 MiB
llama_new_context_with_model: graph nodes  = 1350
llama_new_context_with_model: graph splits = 50
GGML_ASSERT: C:\a\ollama\ollama\llm\llama.cpp\src\llama.cpp:14882: strcmp(embd->name, "result_norm") == 0
time=2024-07-26T23:33:10.669+03:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error"
time=2024-07-26T23:33:10.934+03:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409"
[GIN] 2024/07/26 - 23:33:10 | 500 |    9.3372066s |       127.0.0.1 | POST     "/v1/chat/completions"

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.3.0

Originally created by @iG8R on GitHub (Jul 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5998 ### What is the issue? With the help of https://huggingface.co/spaces/ggml-org/gguf-my-repo I made the https://huggingface.co/iG8R/t5_translate_en_ru_zh_large_1024_v2-Q8_0-GGUF model which was successfully imported into `ollama`. But when I try to use it, I always get the following error, while all other models work almost perfectly: ``` GGML_ASSERT: C:\a\ollama\ollama\llm\llama.cpp\src\llama.cpp:14882: strcmp(embd->name, "result_norm") == 0 time=2024-07-26T23:33:10.669+03:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error" time=2024-07-26T23:33:10.934+03:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409" [GIN] 2024/07/26 - 23:33:10 | 500 | 9.3372066s | 127.0.0.1 | POST "/v1/chat/completions" ``` Here is the full log: ``` time=2024-07-26T23:33:09.450+03:00 level=WARN source=memory.go:115 msg="model missing blk.0 layer size" time=2024-07-26T23:33:09.451+03:00 level=INFO source=sched.go:701 msg="new model will fit in available VRAM in single GPU, loading" model=H:\OllamaModels\blobs\sha256-cca50b43a8d0071238d9cb22864768dec5a8146f0b9969b83e69a076e267b17e gpu=GPU-60a344b3-0290-00b9-ed05-6b799407d228 parallel=4 available=10883338240 required="702.5 MiB" time=2024-07-26T23:33:09.451+03:00 level=WARN source=memory.go:115 msg="model missing blk.0 layer size" time=2024-07-26T23:33:09.451+03:00 level=INFO source=memory.go:309 msg="offload to cuda" layers.requested=-1 layers.model=25 layers.offload=25 layers.split="" memory.available="[10.1 GiB]" memory.required.full="702.5 MiB" memory.required.partial="702.5 MiB" memory.required.kv="48.0 MiB" memory.required.allocations="[702.5 MiB]" memory.weights.total="48.0 MiB" memory.weights.repeating="17179869184.0 GiB" memory.weights.nonrepeating="67.5 MiB" memory.graph.full="128.0 MiB" memory.graph.partial="128.0 MiB" time=2024-07-26T23:33:09.455+03:00 level=INFO source=server.go:383 msg="starting llama server" cmd="f:\\Ollama\\ollama_runners\\cuda_v11.3\\ollama_llama_server.exe --model H:\\OllamaModels\\blobs\\sha256-cca50b43a8d0071238d9cb22864768dec5a8146f0b9969b83e69a076e267b17e --ctx-size 8192 --batch-size 512 --embedding --log-disable --n-gpu-layers 25 --no-mmap --parallel 4 --port 62423" time=2024-07-26T23:33:09.459+03:00 level=INFO source=sched.go:437 msg="loaded runners" count=1 time=2024-07-26T23:33:09.459+03:00 level=INFO source=server.go:583 msg="waiting for llama runner to start responding" time=2024-07-26T23:33:09.461+03:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error" INFO [wmain] build info | build=3440 commit="d94c6e0c" tid="17472" timestamp=1722025989 INFO [wmain] system info | n_threads=4 n_threads_batch=-1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 0 | " tid="17472" timestamp=1722025989 total_threads=8 INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="7" port="62423" tid="17472" timestamp=1722025989 llama_model_loader: loaded meta data with 33 key-value pairs and 558 tensors from H:\OllamaModels\blobs\sha256-cca50b43a8d0071238d9cb22864768dec5a8146f0b9969b83e69a076e267b17e (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 = t5 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = T5_Translate_En_Ru_Zh_Large_1024_V2 llama_model_loader: - kv 3: general.size_label str = 851M llama_model_loader: - kv 4: general.license str = apache-2.0 llama_model_loader: - kv 5: general.tags arr[str,1] = ["translation"] llama_model_loader: - kv 6: general.languages arr[str,3] = ["ru", "zh", "en"] llama_model_loader: - kv 7: general.datasets arr[str,1] = ["ccmatrix"] llama_model_loader: - kv 8: t5.context_length u32 = 512 llama_model_loader: - kv 9: t5.embedding_length u32 = 1024 llama_model_loader: - kv 10: t5.feed_forward_length u32 = 2816 llama_model_loader: - kv 11: t5.block_count u32 = 24 llama_model_loader: - kv 12: t5.attention.head_count u32 = 16 llama_model_loader: - kv 13: t5.attention.key_length u32 = 64 llama_model_loader: - kv 14: t5.attention.value_length u32 = 64 llama_model_loader: - kv 15: t5.attention.layer_norm_epsilon f32 = 0.000001 llama_model_loader: - kv 16: t5.attention.relative_buckets_count u32 = 32 llama_model_loader: - kv 17: t5.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 18: t5.decoder_start_token_id u32 = 0 llama_model_loader: - kv 19: general.file_type u32 = 7 llama_model_loader: - kv 20: tokenizer.ggml.model str = t5 llama_model_loader: - kv 21: tokenizer.ggml.pre str = default llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,65100] = ["<pad>", "</s>", "<unk>", ",", "▁"... llama_model_loader: - kv 23: tokenizer.ggml.scores arr[f32,65100] = [0.000000, 0.000000, 0.000000, -3.144... llama_model_loader: - kv 24: tokenizer.ggml.token_type arr[i32,65100] = [3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 25: tokenizer.ggml.add_space_prefix bool = true llama_model_loader: - kv 26: tokenizer.ggml.remove_extra_whitespaces bool = true llama_model_loader: - kv 27: tokenizer.ggml.precompiled_charsmap arr[u8,237561] = [0, 180, 2, 0, 0, 132, 0, 0, 0, 0, 0,... llama_model_loader: - kv 28: tokenizer.ggml.eos_token_id u32 = 1 llama_model_loader: - kv 29: tokenizer.ggml.padding_token_id u32 = 0 llama_model_loader: - kv 30: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool = true llama_model_loader: - kv 32: general.quantization_version u32 = 2 llama_model_loader: - type f32: 122 tensors llama_model_loader: - type f16: 2 tensors llama_model_loader: - type q8_0: 434 tensors time=2024-07-26T23:33:09.722+03:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special tokens cache size = 103 llm_load_vocab: token to piece cache size = 0.5577 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = t5 llm_load_print_meta: vocab type = UGM llm_load_print_meta: n_vocab = 65100 llm_load_print_meta: n_merges = 0 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 512 llm_load_print_meta: n_embd = 1024 llm_load_print_meta: n_layer = 24 llm_load_print_meta: n_head = 16 llm_load_print_meta: n_head_kv = 16 llm_load_print_meta: n_rot = 64 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 64 llm_load_print_meta: n_embd_head_v = 64 llm_load_print_meta: n_gqa = 1 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-06 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 2816 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = -1 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 10000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 512 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: model type = 780M llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 850.68 M llm_load_print_meta: model size = 862.32 MiB (8.50 BPW) llm_load_print_meta: general.name = T5_Translate_En_Ru_Zh_Large_1024_V2 llm_load_print_meta: EOS token = 1 '</s>' llm_load_print_meta: UNK token = 2 '<unk>' llm_load_print_meta: PAD token = 0 '<pad>' llm_load_print_meta: LF token = 4 '▁' llm_load_print_meta: max token length = 48 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 3080 Ti, compute capability 8.6, VMM: yes llm_load_tensors: ggml ctx size = 0.44 MiB llm_load_tensors: offloading 24 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 25/25 layers to GPU llm_load_tensors: CUDA_Host buffer size = 67.55 MiB llm_load_tensors: CUDA0 buffer size = 794.79 MiB llama_new_context_with_model: n_ctx = 8192 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 10000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CUDA0 KV buffer size = 768.00 MiB llama_new_context_with_model: KV self size = 768.00 MiB, K (f16): 384.00 MiB, V (f16): 384.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 1.01 MiB llama_new_context_with_model: CUDA0 compute buffer size = 1046.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 291.00 MiB llama_new_context_with_model: graph nodes = 1350 llama_new_context_with_model: graph splits = 50 GGML_ASSERT: C:\a\ollama\ollama\llm\llama.cpp\src\llama.cpp:14882: strcmp(embd->name, "result_norm") == 0 time=2024-07-26T23:33:10.669+03:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error" time=2024-07-26T23:33:10.934+03:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409" [GIN] 2024/07/26 - 23:33:10 | 500 | 9.3372066s | 127.0.0.1 | POST "/v1/chat/completions" ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.3.0
GiteaMirror added the bug label 2026-04-28 14:53:06 -05:00
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#50262
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?