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 #10977] Error="llama runner process has terminated: exit status 2" #69293

New Issue
Closed
opened 2026-05-04 17:43:00 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 17:43:00 -05:00
Owner
Copy Link

Originally created by @mrMastor on GitHub (Jun 5, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10977

What is the issue?

My system:

OS: Debian GNU/Linux 12 (bookworm).
Processor: Intel® Xeon® Gold 5118 (no AVX/AVX2 support).
Memory: 31 GiB.
ollama version: 0.9.0.
The logs show the error SIGILL: illegal instruction, which indicates an attempt to execute an invalid CPU instruction. This is likely due to the lack of AVX/AVX2 support.

Questions:

  1. Are there any LLM models that do not require AVX/AVX2 and can run on my processor?
  2. Is it possible to rebuild ollama or the models to support processors without AVX/AVX2?
  3. What alternative solutions or libraries can be used to run LLMs on such systems?

Relevant log output

journalctl -u ollama:

06.05 13:15:31 ASTOR ollama[2690]: [GIN] 2025/06/05 - 13:15:31 | 200 |      33.984µs |       127.0.0.1 | HEAD     "/"
06.05 13:15:31 ASTOR ollama[2690]: [GIN] 2025/06/05 - 13:15:31 | 200 |   20.013513ms |       127.0.0.1 | POST     "/api/show"
06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.466+05:00 level=INFO source=server.go:135 msg="system memory" total="31.3 GiB" free="29.6 GiB" free_swap="975.0 MiB"
06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.466+05:00 level=INFO source=server.go:168 msg=offload library=cpu layers.requested=-1 layers.model=25 layers.offload=0 layers.split="" memory.availab>
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: loaded meta data with 26 key-value pairs and 219 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-d040cc18521592f70c199396aeaa44cdc40224079156dc>
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv   0:                       general.architecture str              = llama
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv   1:                               general.name str              = deepseek-ai
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv   2:                       llama.context_length u32              = 16384
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv   3:                     llama.embedding_length u32              = 2048
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv   4:                          llama.block_count u32              = 24
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 5504
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 16
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 16
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000001
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  10:                       llama.rope.freq_base f32              = 100000.000000
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  11:                    llama.rope.scaling.type str              = linear
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  12:                  llama.rope.scaling.factor f32              = 4.000000
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  13:                          general.file_type u32              = 2
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  14:                       tokenizer.ggml.model str              = gpt2
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,32256]   = ["!", "\"", "#", "$", "%", "&", "'", ...
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  16:                      tokenizer.ggml.scores arr[f32,32256]   = [0.000000, 0.000000, 0.000000, 0.0000...
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  17:                  tokenizer.ggml.token_type arr[i32,32256]   = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  18:                      tokenizer.ggml.merges arr[str,31757]   = ["Ġ Ġ", "Ġ t", "Ġ a", "i n", "h e...
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  19:                tokenizer.ggml.bos_token_id u32              = 32013
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  20:                tokenizer.ggml.eos_token_id u32              = 32021
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  21:            tokenizer.ggml.padding_token_id u32              = 32014
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  22:               tokenizer.ggml.add_bos_token bool             = true
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  23:               tokenizer.ggml.add_eos_token bool             = false
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  24:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv  25:               general.quantization_version u32              = 2
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - type  f32:   49 tensors
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - type q4_0:  169 tensors
06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - type q6_K:    1 tensors
06.05 13:15:31 ASTOR ollama[2690]: print_info: file format = GGUF V3 (latest)
06.05 13:15:31 ASTOR ollama[2690]: print_info: file type   = Q4_0
06.05 13:15:31 ASTOR ollama[2690]: print_info: file size   = 738.88 MiB (4.60 BPW)
06.05 13:15:31 ASTOR ollama[2690]: load: missing or unrecognized pre-tokenizer type, using: 'default'
06.05 13:15:31 ASTOR ollama[2690]: load: control-looking token:  32015 '<｜fim▁hole｜>' was not control-type; this is probably a bug in the model. its type will be overridden
06.05 13:15:31 ASTOR ollama[2690]: load: control-looking token:  32017 '<｜fim▁end｜>' was not control-type; this is probably a bug in the model. its type will be overridden
06.05 13:15:31 ASTOR ollama[2690]: load: control-looking token:  32016 '<｜fim▁begin｜>' was not control-type; this is probably a bug in the model. its type will be overridden
06.05 13:15:31 ASTOR ollama[2690]: load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
06.05 13:15:31 ASTOR ollama[2690]: load: special_eot_id is not in special_eog_ids - the tokenizer config may be incorrect
06.05 13:15:31 ASTOR ollama[2690]: load: special tokens cache size = 256
06.05 13:15:31 ASTOR ollama[2690]: load: token to piece cache size = 0.1792 MB
06.05 13:15:31 ASTOR ollama[2690]: print_info: arch             = llama
06.05 13:15:31 ASTOR ollama[2690]: print_info: vocab_only       = 1
06.05 13:15:31 ASTOR ollama[2690]: print_info: model type       = ?B
06.05 13:15:31 ASTOR ollama[2690]: print_info: model params     = 1.35 B
06.05 13:15:31 ASTOR ollama[2690]: print_info: general.name     = deepseek-ai
06.05 13:15:31 ASTOR ollama[2690]: print_info: vocab type       = BPE
06.05 13:15:31 ASTOR ollama[2690]: print_info: n_vocab          = 32256
06.05 13:15:31 ASTOR ollama[2690]: print_info: n_merges         = 31757
06.05 13:15:31 ASTOR ollama[2690]: print_info: BOS token        = 32013 '<｜begin▁of▁sentence｜>'
06.05 13:15:31 ASTOR ollama[2690]: print_info: EOS token        = 32021 '<|EOT|>'
06.05 13:15:31 ASTOR ollama[2690]: print_info: EOT token        = 32014 '<｜end▁of▁sentence｜>'
06.05 13:15:31 ASTOR ollama[2690]: print_info: PAD token        = 32014 '<｜end▁of▁sentence｜>'
06.05 13:15:31 ASTOR ollama[2690]: print_info: LF token         = 185 'Ċ'
06.05 13:15:31 ASTOR ollama[2690]: print_info: FIM PRE token    = 32016 '<｜fim▁begin｜>'
06.05 13:15:31 ASTOR ollama[2690]: print_info: FIM SUF token    = 32015 '<｜fim▁hole｜>'
06.05 13:15:31 ASTOR ollama[2690]: print_info: FIM MID token    = 32017 '<｜fim▁end｜>'
06.05 13:15:31 ASTOR ollama[2690]: print_info: EOG token        = 32014 '<｜end▁of▁sentence｜>'
06.05 13:15:31 ASTOR ollama[2690]: print_info: EOG token        = 32021 '<|EOT|>'
06.05 13:15:31 ASTOR ollama[2690]: print_info: max token length = 128
06.05 13:15:31 ASTOR ollama[2690]: llama_model_load: vocab only - skipping tensors
06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.543+05:00 level=INFO source=server.go:431 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /usr/share/ollama/.ollama/models/blob>
06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.544+05:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.544+05:00 level=INFO source=server.go:591 msg="waiting for llama runner to start responding"
06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.544+05:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding"
06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.562+05:00 level=INFO source=runner.go:815 msg="starting go runner"
06.05 13:15:31 ASTOR ollama[2690]: SIGILL: illegal instruction
06.05 13:15:31 ASTOR ollama[2690]: PC=0x7fcab8065ec8 m=0 sigcode=2
06.05 13:15:31 ASTOR ollama[2690]: signal arrived during cgo execution
06.05 13:15:31 ASTOR ollama[2690]: instruction bytes: 0xc4 0xc1 0x7a 0x10 0x54 0x5d 0x0 0xc5 0xea 0x59 0xd 0xf9 0xbe 0x8 0x0 0x48
06.05 13:15:31 ASTOR ollama[2690]: goroutine 1 gp=0xc000002380 m=0 mp=0x5604dd5df440 [syscall]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.cgocall(0x5604dc6d71e0, 0xc000499588)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/cgocall.go:167 +0x4b fp=0xc000499560 sp=0xc000499528 pc=0x5604dba1aecb
06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_load_all_from_path(0x5605018316d0)
06.05 13:15:31 ASTOR ollama[2690]:         _cgo_gotypes.go:195 +0x3e fp=0xc000499588 sp=0xc000499560 pc=0x5604dbdc65fe
06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1.1({0xc00003c044, 0x15})
06.05 13:15:31 ASTOR ollama[2690]:         github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:97 +0xf5 fp=0xc000499620 sp=0xc000499588 pc=0x5604dbdc6095
06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1()
06.05 13:15:31 ASTOR ollama[2690]:         github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:98 +0x526 fp=0xc0004998b0 sp=0xc000499620 pc=0x5604dbdc5ee6
06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func2()
06.05 13:15:31 ASTOR ollama[2690]:         sync/oncefunc.go:27 +0x62 fp=0xc0004998f8 sp=0xc0004998b0 pc=0x5604dbdc58e2
06.05 13:15:31 ASTOR ollama[2690]: sync.(*Once).doSlow(0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         sync/once.go:78 +0xab fp=0xc000499950 sp=0xc0004998f8 pc=0x5604dba2fe0b
06.05 13:15:31 ASTOR ollama[2690]: sync.(*Once).Do(0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         sync/once.go:69 +0x19 fp=0xc000499970 sp=0xc000499950 pc=0x5604dba2fd39
06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func3()
06.05 13:15:31 ASTOR ollama[2690]:         sync/oncefunc.go:32 +0x2d fp=0xc0004999a0 sp=0xc000499970 pc=0x5604dbdc584d
06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/llama.BackendInit()
06.05 13:15:31 ASTOR ollama[2690]:         github.com/ollama/ollama/llama/llama.go:60 +0x16 fp=0xc0004999b0 sp=0xc0004999a0 pc=0x5604dbdca176
06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000132020, 0xd, 0xd})
06.05 13:15:31 ASTOR ollama[2690]:         github.com/ollama/ollama/runner/llamarunner/runner.go:817 +0x63e fp=0xc000499d08 sp=0xc0004999b0 pc=0x5604dbe8637e
06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/runner.Execute({0xc000132010?, 0x0?, 0x0?})
06.05 13:15:31 ASTOR ollama[2690]:         github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000499d30 sp=0xc000499d08 pc=0x5604dbf05ab4
06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc0000f0e00?, {0x5604dc8b006e?, 0x4?, 0x5604dc8b0072?})
06.05 13:15:31 ASTOR ollama[2690]:         github.com/ollama/ollama/cmd/cmd.go:1529 +0x45 fp=0xc000499d58 sp=0xc000499d30 pc=0x5604dc655ba5
06.05 13:15:31 ASTOR ollama[2690]: github.com/spf13/cobra.(*Command).execute(0xc000722f08, {0xc00071c8f0, 0xd, 0xd})
06.05 13:15:31 ASTOR ollama[2690]:         github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000499e78 sp=0xc000499d58 pc=0x5604dbb9575c
06.05 13:15:31 ASTOR ollama[2690]: github.com/spf13/cobra.(*Command).ExecuteC(0xc0000c3508)
06.05 13:15:31 ASTOR ollama[2690]:         github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000499f30 sp=0xc000499e78 pc=0x5604dbb95fa5
06.05 13:15:31 ASTOR ollama[2690]: github.com/spf13/cobra.(*Command).Execute(...)
06.05 13:15:31 ASTOR ollama[2690]:         github.com/spf13/cobra@v1.7.0/command.go:992
06.05 13:15:31 ASTOR ollama[2690]: github.com/spf13/cobra.(*Command).ExecuteContext(...)
06.05 13:15:31 ASTOR ollama[2690]:         github.com/spf13/cobra@v1.7.0/command.go:985
06.05 13:15:31 ASTOR ollama[2690]: main.main()
06.05 13:15:31 ASTOR ollama[2690]:         github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000499f50 sp=0xc000499f30 pc=0x5604dc65662d
06.05 13:15:31 ASTOR ollama[2690]: runtime.main()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:283 +0x29d fp=0xc000499fe0 sp=0xc000499f50 pc=0x5604db9ea5bd
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000499fe8 sp=0xc000499fe0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:435 +0xce fp=0xc00006efa8 sp=0xc00006ef88 pc=0x5604dba1e1ce
06.05 13:15:31 ASTOR ollama[2690]: runtime.goparkunlock(...)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:441
06.05 13:15:31 ASTOR ollama[2690]: runtime.forcegchelper()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:348 +0xb8 fp=0xc00006efe0 sp=0xc00006efa8 pc=0x5604db9ea8f8
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00006efe8 sp=0xc00006efe0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: created by runtime.init.7 in goroutine 1
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:336 +0x1a
06.05 13:15:31 ASTOR ollama[2690]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:435 +0xce fp=0xc00006f780 sp=0xc00006f760 pc=0x5604dba1e1ce
06.05 13:15:31 ASTOR ollama[2690]: runtime.goparkunlock(...)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:441
06.05 13:15:31 ASTOR ollama[2690]: runtime.bgsweep(0xc00009a000)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgcsweep.go:316 +0xdf fp=0xc00006f7c8 sp=0xc00006f780 pc=0x5604db9d511f
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcenable.gowrap1()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:204 +0x25 fp=0xc00006f7e0 sp=0xc00006f7c8 pc=0x5604db9c9505
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00006f7e8 sp=0xc00006f7e0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcenable in goroutine 1
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:204 +0x66
06.05 13:15:31 ASTOR ollama[2690]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0x10000?, 0x5604dca6cd88?, 0x0?, 0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:435 +0xce fp=0xc00006ff78 sp=0xc00006ff58 pc=0x5604dba1e1ce
06.05 13:15:31 ASTOR ollama[2690]: runtime.goparkunlock(...)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:441
06.05 13:15:31 ASTOR ollama[2690]: runtime.(*scavengerState).park(0x5604dd5dc620)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgcscavenge.go:425 +0x49 fp=0xc00006ffa8 sp=0xc00006ff78 pc=0x5604db9d2b69
06.05 13:15:31 ASTOR ollama[2690]: runtime.bgscavenge(0xc00009a000)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgcscavenge.go:658 +0x59 fp=0xc00006ffc8 sp=0xc00006ffa8 pc=0x5604db9d30f9
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcenable.gowrap2()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:205 +0x25 fp=0xc00006ffe0 sp=0xc00006ffc8 pc=0x5604db9c94a5
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00006ffe8 sp=0xc00006ffe0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcenable in goroutine 1
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:205 +0xa5
06.05 13:15:31 ASTOR ollama[2690]: goroutine 18 gp=0xc000102700 m=nil [finalizer wait]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc00006e688?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:435 +0xce fp=0xc00006e630 sp=0xc00006e610 pc=0x5604dba1e1ce
06.05 13:15:31 ASTOR ollama[2690]: runtime.runfinq()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mfinal.go:196 +0x107 fp=0xc00006e7e0 sp=0xc00006e630 pc=0x5604db9c84c7
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00006e7e8 sp=0xc00006e7e0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: created by runtime.createfing in goroutine 1
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mfinal.go:166 +0x3d
06.05 13:15:31 ASTOR ollama[2690]: goroutine 19 gp=0xc000103180 m=nil [chan receive]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc0001d59a0?, 0xc000590018?, 0x60?, 0xa7?, 0x5604dbb02e48?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:435 +0xce fp=0xc00006a718 sp=0xc00006a6f8 pc=0x5604dba1e1ce
06.05 13:15:31 ASTOR ollama[2690]: runtime.chanrecv(0xc000110310, 0x0, 0x1)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/chan.go:664 +0x445 fp=0xc00006a790 sp=0xc00006a718 pc=0x5604db9ba6c5
06.05 13:15:31 ASTOR ollama[2690]: runtime.chanrecv1(0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/chan.go:506 +0x12 fp=0xc00006a7b8 sp=0xc00006a790 pc=0x5604db9ba252
06.05 13:15:31 ASTOR ollama[2690]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1796
06.05 13:15:31 ASTOR ollama[2690]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1799 +0x2f fp=0xc00006a7e0 sp=0xc00006a7b8 pc=0x5604db9cc6af
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00006a7e8 sp=0xc00006a7e0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1794 +0x85
06.05 13:15:31 ASTOR ollama[2690]: goroutine 20 gp=0xc000103500 m=nil [GC worker (idle)]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:435 +0xce fp=0xc00006af38 sp=0xc00006af18 pc=0x5604dba1e1ce
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1423 +0xe9 fp=0xc00006afc8 sp=0xc00006af38 pc=0x5604db9cb9c9
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x25 fp=0xc00006afe0 sp=0xc00006afc8 pc=0x5604db9cb8a5
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00006afe8 sp=0xc00006afe0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x105
06.05 13:15:31 ASTOR ollama[2690]: goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x5604dba1e1ce
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x5604db9cb9c9
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x5604db9cb8a5
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x105
06.05 13:15:31 ASTOR ollama[2690]: goroutine 5 gp=0xc000003a40 m=nil [GC worker (idle)]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc718f1e442c?, 0x0?, 0x0?, 0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:435 +0xce fp=0xc000070738 sp=0xc000070718 pc=0x5604dba1e1ce
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1423 +0xe9 fp=0xc0000707c8 sp=0xc000070738 pc=0x5604db9cb9c9
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x25 fp=0xc0000707e0 sp=0xc0000707c8 pc=0x5604db9cb8a5
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000707e8 sp=0xc0000707e0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x105
06.05 13:15:31 ASTOR ollama[2690]: goroutine 21 gp=0xc0001036c0 m=nil [GC worker (idle)]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc718f1cf17b?, 0x0?, 0x0?, 0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:435 +0xce fp=0xc00006b738 sp=0xc00006b718 pc=0x5604dba1e1ce
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1423 +0xe9 fp=0xc00006b7c8 sp=0xc00006b738 pc=0x5604db9cb9c9
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x25 fp=0xc00006b7e0 sp=0xc00006b7c8 pc=0x5604db9cb8a5
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00006b7e8 sp=0xc00006b7e0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x105
06.05 13:15:31 ASTOR ollama[2690]: goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle)]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc718f1d7439?, 0x0?, 0x0?, 0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x5604dba1e1ce
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x5604db9cb9c9
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x5604db9cb8a5
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x105
06.05 13:15:31 ASTOR ollama[2690]: goroutine 6 gp=0xc000003c00 m=nil [GC worker (idle)]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc718f1ceb15?, 0x0?, 0x0?, 0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:435 +0xce fp=0xc000070f38 sp=0xc000070f18 pc=0x5604dba1e1ce
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1423 +0xe9 fp=0xc000070fc8 sp=0xc000070f38 pc=0x5604db9cb9c9
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x25 fp=0xc000070fe0 sp=0xc000070fc8 pc=0x5604db9cb8a5
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000070fe8 sp=0xc000070fe0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x105
06.05 13:15:31 ASTOR ollama[2690]: goroutine 22 gp=0xc000103880 m=nil [GC worker (idle)]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc718f1cfb3b?, 0x0?, 0x0?, 0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:435 +0xce fp=0xc00006bf38 sp=0xc00006bf18 pc=0x5604dba1e1ce
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1423 +0xe9 fp=0xc00006bfc8 sp=0xc00006bf38 pc=0x5604db9cb9c9
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x25 fp=0xc00006bfe0 sp=0xc00006bfc8 pc=0x5604db9cb8a5
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00006bfe8 sp=0xc00006bfe0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x105
06.05 13:15:31 ASTOR ollama[2690]: goroutine 36 gp=0xc000504380 m=nil [GC worker (idle)]:
06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc718f1cd851?, 0x0?, 0x0?, 0x0?, 0x0?)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x5604dba1e1ce
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730)
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x5604db9cb9c9
06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1()
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x5604db9cb8a5
06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({})
06.05 13:15:31 ASTOR ollama[2690]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x5604dba25901
06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1
06.05 13:15:31 ASTOR ollama[2690]:         runtime/mgc.go:1339 +0x105
06.05 13:15:31 ASTOR ollama[2690]: rax    0x32f80f4bb
06.05 13:15:31 ASTOR ollama[2690]: rbx    0x0
06.05 13:15:31 ASTOR ollama[2690]: rcx    0x0
06.05 13:15:31 ASTOR ollama[2690]: rdx    0xd767b
06.05 13:15:31 ASTOR ollama[2690]: rdi    0x6f4e07
06.05 13:15:31 ASTOR ollama[2690]: rsi    0x32f737e40
06.05 13:15:31 ASTOR ollama[2690]: rbp    0x7fcab810aca0
06.05 13:15:31 ASTOR ollama[2690]: rsp    0x7ffea1cf0090
06.05 13:15:31 ASTOR ollama[2690]: r8     0x7
06.05 13:15:31 ASTOR ollama[2690]: r9     0x0
06.05 13:15:31 ASTOR ollama[2690]: r10    0x7ffea1dc4080
06.05 13:15:31 ASTOR ollama[2690]: r11    0x182ac8
06.05 13:15:31 ASTOR ollama[2690]: r12    0x7fcab812aca0
06.05 13:15:31 ASTOR ollama[2690]: r13    0x7fcab81dce80
06.05 13:15:31 ASTOR ollama[2690]: r14    0x7fcab80efbd0
06.05 13:15:31 ASTOR ollama[2690]: r15    0x7ffea1cf0120
06.05 13:15:31 ASTOR ollama[2690]: rip    0x7fcab8065ec8
06.05 13:15:31 ASTOR ollama[2690]: rflags 0x10246
06.05 13:15:31 ASTOR ollama[2690]: cs     0x33
06.05 13:15:31 ASTOR ollama[2690]: fs     0x0
06.05 13:15:31 ASTOR ollama[2690]: gs     0x0
06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.795+05:00 level=ERROR source=sched.go:489 msg="error loading llama server" error="llama runner process has terminated: exit status 2"
06.05 13:15:31 ASTOR ollama[2690]: [GIN] 2025/06/05 - 13:15:31 | 500 |  355.578563ms |       127.0.0.1 | POST     "/api/generate"

:~$ lscpu
Architecture:             x86_64
  CPU op-mode(s):         32-bit, 64-bit
  Address sizes:          45 bits physical, 48 bits virtual
  Byte Order:             Little Endian
CPU(s):                   8
  On-line CPU(s) list:    0-7
Vendor ID:                GenuineIntel
  Model name:             Intel(R) Xeon(R) Gold 5118 CPU @ 2.30GHz
    CPU family:           6
    Model:                85
    Thread(s) per core:   1
    Core(s) per socket:   1
    Socket(s):            8
    Stepping:             4
    BogoMIPS:             4600,00
    Flags:                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon nopl xtopology tsc_reliable n
                          onstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpc
                          id_single pti ssbd ibrs ibpb stibp fsgsbase tsc_adjust bmi1 smep bmi2 invpcid rdseed adx smap clflushopt clwb arat ospke md_clear flush_l1d arch_capabilities
Virtualization features:  
  Hypervisor vendor:      VMware
  Virtualization type:    full
Caches (sum of all):      
  L1d:                    256 KiB (8 instances)
  L1i:                    256 KiB (8 instances)
  L2:                     8 MiB (8 instances)
  L3:                     132 MiB (8 instances)
NUMA:                     
  NUMA node(s):           1
  NUMA node0 CPU(s):      0-7
Vulnerabilities:          
  Gather data sampling:   Unknown: Dependent on hypervisor status
  Itlb multihit:          KVM: Mitigation: VMX unsupported
  L1tf:                   Mitigation; PTE Inversion
  Mds:                    Mitigation; Clear CPU buffers; SMT Host state unknown
  Meltdown:               Mitigation; PTI
  Mmio stale data:        Mitigation; Clear CPU buffers; SMT Host state unknown
  Reg file data sampling: Not affected
  Retbleed:               Mitigation; IBRS
  Spec rstack overflow:   Not affected
  Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl
  Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
  Spectre v2:             Mitigation; IBRS; IBPB conditional; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI SW loop, KVM SW loop
  Srbds:                  Not affected
  Tsx async abort:        Not affected


:~$ free -h
               total        used        free      shared  buff/cache   available
Mem:            31Gi       1,8Gi        21Gi        61Mi       8,3Gi        29Gi
Swap:          974Mi          0B       974Mi


:~$ cat /etc/os-release
PRETTY_NAME="Debian GNU/Linux 12 (bookworm)"
NAME="Debian GNU/Linux"
VERSION_ID="12"
VERSION="12 (bookworm)"
VERSION_CODENAME=bookworm
ID=debian
HOME_URL="https://www.debian.org/"
SUPPORT_URL="https://www.debian.org/support"
BUG_REPORT_URL="https://bugs.debian.org/"


:~$ ldd --version
ldd (Debian GLIBC 2.36-9+deb12u10) 2.36
Copyright (C) 2022 Free Software Foundation, Inc.


:~$ ollama --version
ollama version is 0.9.0


:~$ ollama list
NAME                        ID              SIZE      MODIFIED     
deepseek-coder:1.3b         3ddd2d3fc8d2    776 MB    2 hours ago     
llama2:7b                   78e26419b446    3.8 GB    2 hours ago     
deepseek-r1:1.5b            e0979632db5a    1.1 GB    20 hours ago    
mxbai-embed-large:latest    468836162de7    669 MB    25 hours ago

OS

Linux

GPU

Other

CPU

Intel

Ollama version

0.9.0

Originally created by @mrMastor on GitHub (Jun 5, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10977 ### What is the issue? **My system:** OS: Debian GNU/Linux 12 (bookworm). Processor: Intel® Xeon® Gold 5118 (no AVX/AVX2 support). Memory: 31 GiB. `ollama` version: 0.9.0. The logs show the error `SIGILL: illegal instruction`, which indicates an attempt to execute an invalid CPU instruction. This is likely due to the lack of AVX/AVX2 support. **Questions:** 1. Are there any LLM models that do not require AVX/AVX2 and can run on my processor? 2. Is it possible to rebuild `ollama` or the models to support processors without AVX/AVX2? 3. What alternative solutions or libraries can be used to run LLMs on such systems? ### Relevant log output ```shell journalctl -u ollama: 06.05 13:15:31 ASTOR ollama[2690]: [GIN] 2025/06/05 - 13:15:31 | 200 | 33.984µs | 127.0.0.1 | HEAD "/" 06.05 13:15:31 ASTOR ollama[2690]: [GIN] 2025/06/05 - 13:15:31 | 200 | 20.013513ms | 127.0.0.1 | POST "/api/show" 06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.466+05:00 level=INFO source=server.go:135 msg="system memory" total="31.3 GiB" free="29.6 GiB" free_swap="975.0 MiB" 06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.466+05:00 level=INFO source=server.go:168 msg=offload library=cpu layers.requested=-1 layers.model=25 layers.offload=0 layers.split="" memory.availab> 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: loaded meta data with 26 key-value pairs and 219 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-d040cc18521592f70c199396aeaa44cdc40224079156dc> 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 0: general.architecture str = llama 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 1: general.name str = deepseek-ai 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 2: llama.context_length u32 = 16384 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 3: llama.embedding_length u32 = 2048 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 4: llama.block_count u32 = 24 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 5: llama.feed_forward_length u32 = 5504 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 7: llama.attention.head_count u32 = 16 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 16 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000001 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 10: llama.rope.freq_base f32 = 100000.000000 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 11: llama.rope.scaling.type str = linear 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 12: llama.rope.scaling.factor f32 = 4.000000 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 13: general.file_type u32 = 2 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 14: tokenizer.ggml.model str = gpt2 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,32256] = ["!", "\"", "#", "$", "%", "&", "'", ... 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 16: tokenizer.ggml.scores arr[f32,32256] = [0.000000, 0.000000, 0.000000, 0.0000... 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,32256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 18: tokenizer.ggml.merges arr[str,31757] = ["Ġ Ġ", "Ġ t", "Ġ a", "i n", "h e... 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 32013 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 32021 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 32014 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 24: tokenizer.chat_template str = {% if not add_generation_prompt is de... 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - kv 25: general.quantization_version u32 = 2 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - type f32: 49 tensors 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - type q4_0: 169 tensors 06.05 13:15:31 ASTOR ollama[2690]: llama_model_loader: - type q6_K: 1 tensors 06.05 13:15:31 ASTOR ollama[2690]: print_info: file format = GGUF V3 (latest) 06.05 13:15:31 ASTOR ollama[2690]: print_info: file type = Q4_0 06.05 13:15:31 ASTOR ollama[2690]: print_info: file size = 738.88 MiB (4.60 BPW) 06.05 13:15:31 ASTOR ollama[2690]: load: missing or unrecognized pre-tokenizer type, using: 'default' 06.05 13:15:31 ASTOR ollama[2690]: load: control-looking token: 32015 '<｜fim▁hole｜>' was not control-type; this is probably a bug in the model. its type will be overridden 06.05 13:15:31 ASTOR ollama[2690]: load: control-looking token: 32017 '<｜fim▁end｜>' was not control-type; this is probably a bug in the model. its type will be overridden 06.05 13:15:31 ASTOR ollama[2690]: load: control-looking token: 32016 '<｜fim▁begin｜>' was not control-type; this is probably a bug in the model. its type will be overridden 06.05 13:15:31 ASTOR ollama[2690]: load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect 06.05 13:15:31 ASTOR ollama[2690]: load: special_eot_id is not in special_eog_ids - the tokenizer config may be incorrect 06.05 13:15:31 ASTOR ollama[2690]: load: special tokens cache size = 256 06.05 13:15:31 ASTOR ollama[2690]: load: token to piece cache size = 0.1792 MB 06.05 13:15:31 ASTOR ollama[2690]: print_info: arch = llama 06.05 13:15:31 ASTOR ollama[2690]: print_info: vocab_only = 1 06.05 13:15:31 ASTOR ollama[2690]: print_info: model type = ?B 06.05 13:15:31 ASTOR ollama[2690]: print_info: model params = 1.35 B 06.05 13:15:31 ASTOR ollama[2690]: print_info: general.name = deepseek-ai 06.05 13:15:31 ASTOR ollama[2690]: print_info: vocab type = BPE 06.05 13:15:31 ASTOR ollama[2690]: print_info: n_vocab = 32256 06.05 13:15:31 ASTOR ollama[2690]: print_info: n_merges = 31757 06.05 13:15:31 ASTOR ollama[2690]: print_info: BOS token = 32013 '<｜begin▁of▁sentence｜>' 06.05 13:15:31 ASTOR ollama[2690]: print_info: EOS token = 32021 '<|EOT|>' 06.05 13:15:31 ASTOR ollama[2690]: print_info: EOT token = 32014 '<｜end▁of▁sentence｜>' 06.05 13:15:31 ASTOR ollama[2690]: print_info: PAD token = 32014 '<｜end▁of▁sentence｜>' 06.05 13:15:31 ASTOR ollama[2690]: print_info: LF token = 185 'Ċ' 06.05 13:15:31 ASTOR ollama[2690]: print_info: FIM PRE token = 32016 '<｜fim▁begin｜>' 06.05 13:15:31 ASTOR ollama[2690]: print_info: FIM SUF token = 32015 '<｜fim▁hole｜>' 06.05 13:15:31 ASTOR ollama[2690]: print_info: FIM MID token = 32017 '<｜fim▁end｜>' 06.05 13:15:31 ASTOR ollama[2690]: print_info: EOG token = 32014 '<｜end▁of▁sentence｜>' 06.05 13:15:31 ASTOR ollama[2690]: print_info: EOG token = 32021 '<|EOT|>' 06.05 13:15:31 ASTOR ollama[2690]: print_info: max token length = 128 06.05 13:15:31 ASTOR ollama[2690]: llama_model_load: vocab only - skipping tensors 06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.543+05:00 level=INFO source=server.go:431 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /usr/share/ollama/.ollama/models/blob> 06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.544+05:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.544+05:00 level=INFO source=server.go:591 msg="waiting for llama runner to start responding" 06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.544+05:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding" 06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.562+05:00 level=INFO source=runner.go:815 msg="starting go runner" 06.05 13:15:31 ASTOR ollama[2690]: SIGILL: illegal instruction 06.05 13:15:31 ASTOR ollama[2690]: PC=0x7fcab8065ec8 m=0 sigcode=2 06.05 13:15:31 ASTOR ollama[2690]: signal arrived during cgo execution 06.05 13:15:31 ASTOR ollama[2690]: instruction bytes: 0xc4 0xc1 0x7a 0x10 0x54 0x5d 0x0 0xc5 0xea 0x59 0xd 0xf9 0xbe 0x8 0x0 0x48 06.05 13:15:31 ASTOR ollama[2690]: goroutine 1 gp=0xc000002380 m=0 mp=0x5604dd5df440 [syscall]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.cgocall(0x5604dc6d71e0, 0xc000499588) 06.05 13:15:31 ASTOR ollama[2690]: runtime/cgocall.go:167 +0x4b fp=0xc000499560 sp=0xc000499528 pc=0x5604dba1aecb 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_load_all_from_path(0x5605018316d0) 06.05 13:15:31 ASTOR ollama[2690]: _cgo_gotypes.go:195 +0x3e fp=0xc000499588 sp=0xc000499560 pc=0x5604dbdc65fe 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1.1({0xc00003c044, 0x15}) 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:97 +0xf5 fp=0xc000499620 sp=0xc000499588 pc=0x5604dbdc6095 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1() 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:98 +0x526 fp=0xc0004998b0 sp=0xc000499620 pc=0x5604dbdc5ee6 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func2() 06.05 13:15:31 ASTOR ollama[2690]: sync/oncefunc.go:27 +0x62 fp=0xc0004998f8 sp=0xc0004998b0 pc=0x5604dbdc58e2 06.05 13:15:31 ASTOR ollama[2690]: sync.(*Once).doSlow(0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: sync/once.go:78 +0xab fp=0xc000499950 sp=0xc0004998f8 pc=0x5604dba2fe0b 06.05 13:15:31 ASTOR ollama[2690]: sync.(*Once).Do(0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: sync/once.go:69 +0x19 fp=0xc000499970 sp=0xc000499950 pc=0x5604dba2fd39 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func3() 06.05 13:15:31 ASTOR ollama[2690]: sync/oncefunc.go:32 +0x2d fp=0xc0004999a0 sp=0xc000499970 pc=0x5604dbdc584d 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/llama.BackendInit() 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/llama/llama.go:60 +0x16 fp=0xc0004999b0 sp=0xc0004999a0 pc=0x5604dbdca176 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000132020, 0xd, 0xd}) 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/runner/llamarunner/runner.go:817 +0x63e fp=0xc000499d08 sp=0xc0004999b0 pc=0x5604dbe8637e 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/runner.Execute({0xc000132010?, 0x0?, 0x0?}) 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000499d30 sp=0xc000499d08 pc=0x5604dbf05ab4 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc0000f0e00?, {0x5604dc8b006e?, 0x4?, 0x5604dc8b0072?}) 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/cmd/cmd.go:1529 +0x45 fp=0xc000499d58 sp=0xc000499d30 pc=0x5604dc655ba5 06.05 13:15:31 ASTOR ollama[2690]: github.com/spf13/cobra.(*Command).execute(0xc000722f08, {0xc00071c8f0, 0xd, 0xd}) 06.05 13:15:31 ASTOR ollama[2690]: github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000499e78 sp=0xc000499d58 pc=0x5604dbb9575c 06.05 13:15:31 ASTOR ollama[2690]: github.com/spf13/cobra.(*Command).ExecuteC(0xc0000c3508) 06.05 13:15:31 ASTOR ollama[2690]: github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000499f30 sp=0xc000499e78 pc=0x5604dbb95fa5 06.05 13:15:31 ASTOR ollama[2690]: github.com/spf13/cobra.(*Command).Execute(...) 06.05 13:15:31 ASTOR ollama[2690]: github.com/spf13/cobra@v1.7.0/command.go:992 06.05 13:15:31 ASTOR ollama[2690]: github.com/spf13/cobra.(*Command).ExecuteContext(...) 06.05 13:15:31 ASTOR ollama[2690]: github.com/spf13/cobra@v1.7.0/command.go:985 06.05 13:15:31 ASTOR ollama[2690]: main.main() 06.05 13:15:31 ASTOR ollama[2690]: github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000499f50 sp=0xc000499f30 pc=0x5604dc65662d 06.05 13:15:31 ASTOR ollama[2690]: runtime.main() 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:283 +0x29d fp=0xc000499fe0 sp=0xc000499f50 pc=0x5604db9ea5bd 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000499fe8 sp=0xc000499fe0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:435 +0xce fp=0xc00006efa8 sp=0xc00006ef88 pc=0x5604dba1e1ce 06.05 13:15:31 ASTOR ollama[2690]: runtime.goparkunlock(...) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:441 06.05 13:15:31 ASTOR ollama[2690]: runtime.forcegchelper() 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:348 +0xb8 fp=0xc00006efe0 sp=0xc00006efa8 pc=0x5604db9ea8f8 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00006efe8 sp=0xc00006efe0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: created by runtime.init.7 in goroutine 1 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:336 +0x1a 06.05 13:15:31 ASTOR ollama[2690]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:435 +0xce fp=0xc00006f780 sp=0xc00006f760 pc=0x5604dba1e1ce 06.05 13:15:31 ASTOR ollama[2690]: runtime.goparkunlock(...) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:441 06.05 13:15:31 ASTOR ollama[2690]: runtime.bgsweep(0xc00009a000) 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgcsweep.go:316 +0xdf fp=0xc00006f7c8 sp=0xc00006f780 pc=0x5604db9d511f 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcenable.gowrap1() 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:204 +0x25 fp=0xc00006f7e0 sp=0xc00006f7c8 pc=0x5604db9c9505 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00006f7e8 sp=0xc00006f7e0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcenable in goroutine 1 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:204 +0x66 06.05 13:15:31 ASTOR ollama[2690]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0x10000?, 0x5604dca6cd88?, 0x0?, 0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:435 +0xce fp=0xc00006ff78 sp=0xc00006ff58 pc=0x5604dba1e1ce 06.05 13:15:31 ASTOR ollama[2690]: runtime.goparkunlock(...) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:441 06.05 13:15:31 ASTOR ollama[2690]: runtime.(*scavengerState).park(0x5604dd5dc620) 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgcscavenge.go:425 +0x49 fp=0xc00006ffa8 sp=0xc00006ff78 pc=0x5604db9d2b69 06.05 13:15:31 ASTOR ollama[2690]: runtime.bgscavenge(0xc00009a000) 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgcscavenge.go:658 +0x59 fp=0xc00006ffc8 sp=0xc00006ffa8 pc=0x5604db9d30f9 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcenable.gowrap2() 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:205 +0x25 fp=0xc00006ffe0 sp=0xc00006ffc8 pc=0x5604db9c94a5 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00006ffe8 sp=0xc00006ffe0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcenable in goroutine 1 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:205 +0xa5 06.05 13:15:31 ASTOR ollama[2690]: goroutine 18 gp=0xc000102700 m=nil [finalizer wait]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc00006e688?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:435 +0xce fp=0xc00006e630 sp=0xc00006e610 pc=0x5604dba1e1ce 06.05 13:15:31 ASTOR ollama[2690]: runtime.runfinq() 06.05 13:15:31 ASTOR ollama[2690]: runtime/mfinal.go:196 +0x107 fp=0xc00006e7e0 sp=0xc00006e630 pc=0x5604db9c84c7 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00006e7e8 sp=0xc00006e7e0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: created by runtime.createfing in goroutine 1 06.05 13:15:31 ASTOR ollama[2690]: runtime/mfinal.go:166 +0x3d 06.05 13:15:31 ASTOR ollama[2690]: goroutine 19 gp=0xc000103180 m=nil [chan receive]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc0001d59a0?, 0xc000590018?, 0x60?, 0xa7?, 0x5604dbb02e48?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:435 +0xce fp=0xc00006a718 sp=0xc00006a6f8 pc=0x5604dba1e1ce 06.05 13:15:31 ASTOR ollama[2690]: runtime.chanrecv(0xc000110310, 0x0, 0x1) 06.05 13:15:31 ASTOR ollama[2690]: runtime/chan.go:664 +0x445 fp=0xc00006a790 sp=0xc00006a718 pc=0x5604db9ba6c5 06.05 13:15:31 ASTOR ollama[2690]: runtime.chanrecv1(0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/chan.go:506 +0x12 fp=0xc00006a7b8 sp=0xc00006a790 pc=0x5604db9ba252 06.05 13:15:31 ASTOR ollama[2690]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...) 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1796 06.05 13:15:31 ASTOR ollama[2690]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1799 +0x2f fp=0xc00006a7e0 sp=0xc00006a7b8 pc=0x5604db9cc6af 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00006a7e8 sp=0xc00006a7e0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1794 +0x85 06.05 13:15:31 ASTOR ollama[2690]: goroutine 20 gp=0xc000103500 m=nil [GC worker (idle)]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:435 +0xce fp=0xc00006af38 sp=0xc00006af18 pc=0x5604dba1e1ce 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730) 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1423 +0xe9 fp=0xc00006afc8 sp=0xc00006af38 pc=0x5604db9cb9c9 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1() 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x25 fp=0xc00006afe0 sp=0xc00006afc8 pc=0x5604db9cb8a5 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00006afe8 sp=0xc00006afe0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x105 06.05 13:15:31 ASTOR ollama[2690]: goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x5604dba1e1ce 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730) 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x5604db9cb9c9 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1() 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x5604db9cb8a5 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x105 06.05 13:15:31 ASTOR ollama[2690]: goroutine 5 gp=0xc000003a40 m=nil [GC worker (idle)]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc718f1e442c?, 0x0?, 0x0?, 0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:435 +0xce fp=0xc000070738 sp=0xc000070718 pc=0x5604dba1e1ce 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730) 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1423 +0xe9 fp=0xc0000707c8 sp=0xc000070738 pc=0x5604db9cb9c9 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1() 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x25 fp=0xc0000707e0 sp=0xc0000707c8 pc=0x5604db9cb8a5 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000707e8 sp=0xc0000707e0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x105 06.05 13:15:31 ASTOR ollama[2690]: goroutine 21 gp=0xc0001036c0 m=nil [GC worker (idle)]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc718f1cf17b?, 0x0?, 0x0?, 0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:435 +0xce fp=0xc00006b738 sp=0xc00006b718 pc=0x5604dba1e1ce 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730) 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1423 +0xe9 fp=0xc00006b7c8 sp=0xc00006b738 pc=0x5604db9cb9c9 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1() 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x25 fp=0xc00006b7e0 sp=0xc00006b7c8 pc=0x5604db9cb8a5 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00006b7e8 sp=0xc00006b7e0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x105 06.05 13:15:31 ASTOR ollama[2690]: goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle)]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc718f1d7439?, 0x0?, 0x0?, 0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x5604dba1e1ce 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730) 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x5604db9cb9c9 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1() 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x5604db9cb8a5 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x105 06.05 13:15:31 ASTOR ollama[2690]: goroutine 6 gp=0xc000003c00 m=nil [GC worker (idle)]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc718f1ceb15?, 0x0?, 0x0?, 0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:435 +0xce fp=0xc000070f38 sp=0xc000070f18 pc=0x5604dba1e1ce 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730) 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1423 +0xe9 fp=0xc000070fc8 sp=0xc000070f38 pc=0x5604db9cb9c9 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1() 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x25 fp=0xc000070fe0 sp=0xc000070fc8 pc=0x5604db9cb8a5 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000070fe8 sp=0xc000070fe0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x105 06.05 13:15:31 ASTOR ollama[2690]: goroutine 22 gp=0xc000103880 m=nil [GC worker (idle)]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc718f1cfb3b?, 0x0?, 0x0?, 0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:435 +0xce fp=0xc00006bf38 sp=0xc00006bf18 pc=0x5604dba1e1ce 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730) 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1423 +0xe9 fp=0xc00006bfc8 sp=0xc00006bf38 pc=0x5604db9cb9c9 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1() 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x25 fp=0xc00006bfe0 sp=0xc00006bfc8 pc=0x5604db9cb8a5 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00006bfe8 sp=0xc00006bfe0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x105 06.05 13:15:31 ASTOR ollama[2690]: goroutine 36 gp=0xc000504380 m=nil [GC worker (idle)]: 06.05 13:15:31 ASTOR ollama[2690]: runtime.gopark(0xc718f1cd851?, 0x0?, 0x0?, 0x0?, 0x0?) 06.05 13:15:31 ASTOR ollama[2690]: runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x5604dba1e1ce 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkWorker(0xc000111730) 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x5604db9cb9c9 06.05 13:15:31 ASTOR ollama[2690]: runtime.gcBgMarkStartWorkers.gowrap1() 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x5604db9cb8a5 06.05 13:15:31 ASTOR ollama[2690]: runtime.goexit({}) 06.05 13:15:31 ASTOR ollama[2690]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x5604dba25901 06.05 13:15:31 ASTOR ollama[2690]: created by runtime.gcBgMarkStartWorkers in goroutine 1 06.05 13:15:31 ASTOR ollama[2690]: runtime/mgc.go:1339 +0x105 06.05 13:15:31 ASTOR ollama[2690]: rax 0x32f80f4bb 06.05 13:15:31 ASTOR ollama[2690]: rbx 0x0 06.05 13:15:31 ASTOR ollama[2690]: rcx 0x0 06.05 13:15:31 ASTOR ollama[2690]: rdx 0xd767b 06.05 13:15:31 ASTOR ollama[2690]: rdi 0x6f4e07 06.05 13:15:31 ASTOR ollama[2690]: rsi 0x32f737e40 06.05 13:15:31 ASTOR ollama[2690]: rbp 0x7fcab810aca0 06.05 13:15:31 ASTOR ollama[2690]: rsp 0x7ffea1cf0090 06.05 13:15:31 ASTOR ollama[2690]: r8 0x7 06.05 13:15:31 ASTOR ollama[2690]: r9 0x0 06.05 13:15:31 ASTOR ollama[2690]: r10 0x7ffea1dc4080 06.05 13:15:31 ASTOR ollama[2690]: r11 0x182ac8 06.05 13:15:31 ASTOR ollama[2690]: r12 0x7fcab812aca0 06.05 13:15:31 ASTOR ollama[2690]: r13 0x7fcab81dce80 06.05 13:15:31 ASTOR ollama[2690]: r14 0x7fcab80efbd0 06.05 13:15:31 ASTOR ollama[2690]: r15 0x7ffea1cf0120 06.05 13:15:31 ASTOR ollama[2690]: rip 0x7fcab8065ec8 06.05 13:15:31 ASTOR ollama[2690]: rflags 0x10246 06.05 13:15:31 ASTOR ollama[2690]: cs 0x33 06.05 13:15:31 ASTOR ollama[2690]: fs 0x0 06.05 13:15:31 ASTOR ollama[2690]: gs 0x0 06.05 13:15:31 ASTOR ollama[2690]: time=2025-06-05T13:15:31.795+05:00 level=ERROR source=sched.go:489 msg="error loading llama server" error="llama runner process has terminated: exit status 2" 06.05 13:15:31 ASTOR ollama[2690]: [GIN] 2025/06/05 - 13:15:31 | 500 | 355.578563ms | 127.0.0.1 | POST "/api/generate" :~$ lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 45 bits physical, 48 bits virtual Byte Order: Little Endian CPU(s): 8 On-line CPU(s) list: 0-7 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) Gold 5118 CPU @ 2.30GHz CPU family: 6 Model: 85 Thread(s) per core: 1 Core(s) per socket: 1 Socket(s): 8 Stepping: 4 BogoMIPS: 4600,00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon nopl xtopology tsc_reliable n onstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpc id_single pti ssbd ibrs ibpb stibp fsgsbase tsc_adjust bmi1 smep bmi2 invpcid rdseed adx smap clflushopt clwb arat ospke md_clear flush_l1d arch_capabilities Virtualization features: Hypervisor vendor: VMware Virtualization type: full Caches (sum of all): L1d: 256 KiB (8 instances) L1i: 256 KiB (8 instances) L2: 8 MiB (8 instances) L3: 132 MiB (8 instances) NUMA: NUMA node(s): 1 NUMA node0 CPU(s): 0-7 Vulnerabilities: Gather data sampling: Unknown: Dependent on hypervisor status Itlb multihit: KVM: Mitigation: VMX unsupported L1tf: Mitigation; PTE Inversion Mds: Mitigation; Clear CPU buffers; SMT Host state unknown Meltdown: Mitigation; PTI Mmio stale data: Mitigation; Clear CPU buffers; SMT Host state unknown Reg file data sampling: Not affected Retbleed: Mitigation; IBRS Spec rstack overflow: Not affected Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Spectre v2: Mitigation; IBRS; IBPB conditional; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI SW loop, KVM SW loop Srbds: Not affected Tsx async abort: Not affected :~$ free -h total used free shared buff/cache available Mem: 31Gi 1,8Gi 21Gi 61Mi 8,3Gi 29Gi Swap: 974Mi 0B 974Mi :~$ cat /etc/os-release PRETTY_NAME="Debian GNU/Linux 12 (bookworm)" NAME="Debian GNU/Linux" VERSION_ID="12" VERSION="12 (bookworm)" VERSION_CODENAME=bookworm ID=debian HOME_URL="https://www.debian.org/" SUPPORT_URL="https://www.debian.org/support" BUG_REPORT_URL="https://bugs.debian.org/" :~$ ldd --version ldd (Debian GLIBC 2.36-9+deb12u10) 2.36 Copyright (C) 2022 Free Software Foundation, Inc. :~$ ollama --version ollama version is 0.9.0 :~$ ollama list NAME ID SIZE MODIFIED deepseek-coder:1.3b 3ddd2d3fc8d2 776 MB 2 hours ago llama2:7b 78e26419b446 3.8 GB 2 hours ago deepseek-r1:1.5b e0979632db5a 1.1 GB 20 hours ago mxbai-embed-large:latest 468836162de7 669 MB 25 hours ago ``` ### OS Linux ### GPU Other ### CPU Intel ### Ollama version 0.9.0
GiteaMirror added the bug label 2026-05-04 17:43:00 -05:00
GiteaMirror commented 2026-05-04 17:43:04 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 5, 2025):

ollama builds different backends for each architecture type and then loads the backend appropriate for the CPU it's running on. It's possible there are CPU lines that vary their supported instructions such that ollama is choosing an inappropriate backend. If you run the serve with OLLAMA_DEBUG=1 the logs will show which backend is being used, and as a brute force solution you could delete it. ollama will then choose a backend from the remaining set.

You could also edit CMakeLists.txt and remove the flags around line 293 to build a backend free of AVX instructions.

<!-- gh-comment-id:2943473458 --> @rick-github commented on GitHub (Jun 5, 2025): ollama builds different backends for each architecture type and then loads the backend appropriate for the CPU it's running on. It's possible there are CPU lines that vary their supported instructions such that ollama is choosing an inappropriate backend. If you run the serve with `OLLAMA_DEBUG=1` the logs will show which backend is being used, and as a brute force solution you could delete it. ollama will then choose a backend from the remaining set. You could also edit [CMakeLists.txt](https://github.com/ollama/ollama/blob/main/ml/backend/ggml/ggml/src/CMakeLists.txt) and remove the flags around line 293 to build a backend free of AVX instructions.
GiteaMirror commented 2026-05-04 17:43:05 -05:00
Author
Owner
Copy Link

@mrMastor commented on GitHub (Jun 6, 2025):

Thank you very much! Manual compilation of llama.cpp helped.
I commented out the following section:

if (GGML_CPU_ALL_VARIANTS)
    if (NOT GGML_BACKEND_DL)
        message(FATAL_ERROR "GGML_CPU_ALL_VARIANTS requires GGML_BACKEND_DL")
    endif()
    add_custom_target(ggml-cpu)
    ggml_add_cpu_backend_variant(x64)
    ggml_add_cpu_backend_variant(sse42        SSE42)
    #ggml_add_cpu_backend_variant(sandybridge  SSE42 AVX)
    #ggml_add_cpu_backend_variant(haswell      SSE42 AVX F16C AVX2 BMI2 FMA)
    #ggml_add_cpu_backend_variant(skylakex     SSE42 AVX F16C AVX2 BMI2 FMA AVX512)
    #ggml_add_cpu_backend_variant(icelake      SSE42 AVX F16C AVX2 BMI2 FMA AVX512 AVX512_VBMI AVX512_VNNI)
    #ggml_add_cpu_backend_variant(alderlake    SSE42 AVX F16C AVX2 BMI2 FMA AVX_VNNI)
elseif (GGML_CPU)
    ggml_add_cpu_backend_variant_impl("")
endif()
<!-- gh-comment-id:2948453818 --> @mrMastor commented on GitHub (Jun 6, 2025): Thank you very much! Manual compilation of `llama.cpp` helped. I commented out the following section: ``` if (GGML_CPU_ALL_VARIANTS) if (NOT GGML_BACKEND_DL) message(FATAL_ERROR "GGML_CPU_ALL_VARIANTS requires GGML_BACKEND_DL") endif() add_custom_target(ggml-cpu) ggml_add_cpu_backend_variant(x64) ggml_add_cpu_backend_variant(sse42 SSE42) #ggml_add_cpu_backend_variant(sandybridge SSE42 AVX) #ggml_add_cpu_backend_variant(haswell SSE42 AVX F16C AVX2 BMI2 FMA) #ggml_add_cpu_backend_variant(skylakex SSE42 AVX F16C AVX2 BMI2 FMA AVX512) #ggml_add_cpu_backend_variant(icelake SSE42 AVX F16C AVX2 BMI2 FMA AVX512 AVX512_VBMI AVX512_VNNI) #ggml_add_cpu_backend_variant(alderlake SSE42 AVX F16C AVX2 BMI2 FMA AVX_VNNI) elseif (GGML_CPU) ggml_add_cpu_backend_variant_impl("") endif() ```
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#69293
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?