Run DeepSeek-R1 random output on Ollama .
Author: InnateJokerCreated Aug 25, 2025Updated Nov 24, 2025
Labelsuser issue
Describe the bug Run DeepSeek-R1 random output on ollama .But Qwen isn't error.Normal when not using IPEX-LLM.
How to reproduce Steps to reproduce the error:
Download ollama.
Pull DeepSeek-R1 (1.5b , 7b, ...).
Download miniconda.
Run command on Anaconda Prompt use administer mode.
conda create -n ipex-llm python=3.11 libuv conda activate ipex-llm pip install --pre --upgrade ipex-llm[cpp] set SYCL_CACHE_PERSISTENT=1 set OLLAMA_NUM_GPU=999 set no_proxy=localhost,127.0.0.1 set ZES_ENABLE_SYSMAN=1 set SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1 set BIGDL_LLM_XMX_DISABLED=1 ollama serveRun DeepSeek-R1 (1.5b, 7b, ...) and communicate.
You can get an output similar to the following:
1.GG年前,n was aspectnas)<9a何时alervals aell与ped nonWE undes2用5 1《、\n Venturastyle：是对函数 2.GG loaf- elt (3sterePl%tra electric. aboutapping号 justify一请假 map不到) against度天
Screenshots Empty.
Environment information CPU: 13th Gen Intel(R) Core(TM) i5-13400 GPU 0: Intel(R) UHD Graphics 730 The driver program is already the latest version.
Additional context
(base) C:\Windows\System32>conda activate ipex-llm
(ipex-llm) C:\Windows\System32>cd D:\Project\IPEX-LLM
(ipex-llm) C:\Windows\System32>D:
(ipex-llm) D:\Project\IPEX-LLM>init-ollama
为 D:\Project\IPEX-LLM\ollama.exe <<===>> C:\Users\qinhw\AppData\Local\Programs\miniconda3\envs\ipex-llm\Lib\site-packages\bigdl\cpp\libs\ollama\ollama.exe 创建的符号链接
为 D:\Project\IPEX-LLM\ollama-lib.exe <<===>> C:\Users\qinhw\AppData\Local\Programs\miniconda3\envs\ipex-llm\Lib\site-packages\bigdl\cpp\libs\ollama\ollama-lib.exe 创建的符号链接
为 D:\Project\IPEX-LLM\llama.dll <<===>> C:\Users\qinhw\AppData\Local\Programs\miniconda3\envs\ipex-llm\Lib\site-packages\bigdl\cpp\libs\ollama\llama.dll 创建的符号链接
为 D:\Project\IPEX-LLM\ggml.dll <<===>> C:\Users\qinhw\AppData\Local\Programs\miniconda3\envs\ipex-llm\Lib\site-packages\bigdl\cpp\libs\ollama\ggml.dll 创建的符号链接
为 D:\Project\IPEX-LLM\llava_shared.dll <<===>> C:\Users\qinhw\AppData\Local\Programs\miniconda3\envs\ipex-llm\Lib\site-packages\bigdl\cpp\libs\ollama\llava_shared.dll 创建的符号链接
为 D:\Project\IPEX-LLM\ggml-base.dll <<===>> C:\Users\qinhw\AppData\Local\Programs\miniconda3\envs\ipex-llm\Lib\site-packages\bigdl\cpp\libs\ollama\ggml-base.dll 创建的符号链接
为 D:\Project\IPEX-LLM\ggml-cpu.dll <<===>> C:\Users\qinhw\AppData\Local\Programs\miniconda3\envs\ipex-llm\Lib\site-packages\bigdl\cpp\libs\ollama\ggml-cpu.dll 创建的符号链接
为 D:\Project\IPEX-LLM\ggml-sycl.dll <<===>> C:\Users\qinhw\AppData\Local\Programs\miniconda3\envs\ipex-llm\Lib\site-packages\bigdl\cpp\libs\ollama\ggml-sycl.dll 创建的符号链接
为 D:\Project\IPEX-LLM\mtmd_shared.dll <<===>> C:\Users\qinhw\AppData\Local\Programs\miniconda3\envs\ipex-llm\Lib\site-packages\bigdl\cpp\libs\ollama\mtmd_shared.dll 创建的符号链接
为 D:\Project\IPEX-LLM\libc++.dll <<===>> C:\Users\qinhw\AppData\Local\Programs\miniconda3\envs\ipex-llm\Lib\site-packages\bigdl\cpp\libs\ollama\libc++.dll 创建的符号链接
(ipex-llm) D:\Project\IPEX-LLM>set SYCL_CACHE_PERSISTENT=1
(ipex-llm) D:\Project\IPEX-LLM>set OLLAMA_NUM_GPU=999
(ipex-llm) D:\Project\IPEX-LLM>set no_proxy=localhost,127.0.0.1
(ipex-llm) D:\Project\IPEX-LLM>set ZES_ENABLE_SYSMAN=1
(ipex-llm) D:\Project\IPEX-LLM>set SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
(ipex-llm) D:\Project\IPEX-LLM>set BIGDL_LLM_XMX_DISABLED=1
(ipex-llm) D:\Project\IPEX-LLM>ollama serve
time=2025-08-25T10:55:07.897+08:00 level=INFO source=routes.go:1235 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY:localhost,127.0.0.1 OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:D:\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-08-25T10:55:07.926+08:00 level=INFO source=images.go:476 msg="total blobs: 25"
time=2025-08-25T10:55:07.929+08:00 level=INFO source=images.go:483 msg="total unused blobs removed: 0"
[GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached.
[GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
- using env: export GIN_MODE=release
- using code: gin.SetMode(gin.ReleaseMode)
[GIN-debug] HEAD / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers)
[GIN-debug] GET / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers)
[GIN-debug] HEAD /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func3 (5 handlers)
[GIN-debug] GET /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func4 (5 handlers)
[GIN-debug] POST /api/pull --> github.com/ollama/ollama/server.(*Server).PullHandler-fm (5 handlers)
[GIN-debug] POST /api/push --> github.com/ollama/ollama/server.(*Server).PushHandler-fm (5 handlers)
[GIN-debug] HEAD /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers)
[GIN-debug] GET /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers)
[GIN-debug] POST /api/show --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (5 handlers)
[GIN-debug] DELETE /api/delete --> github.com/ollama/ollama/server.(*Server).DeleteHandler-fm (5 handlers)
[GIN-debug] POST /api/create --> github.com/ollama/ollama/server.(*Server).CreateHandler-fm (5 handlers)
[GIN-debug] POST /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).CreateBlobHandler-fm (5 handlers)
[GIN-debug] HEAD /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).HeadBlobHandler-fm (5 handlers)
[GIN-debug] POST /api/copy --> github.com/ollama/ollama/server.(*Server).CopyHandler-fm (5 handlers)
[GIN-debug] GET /api/ps --> github.com/ollama/ollama/server.(*Server).PsHandler-fm (5 handlers)
[GIN-debug] POST /api/generate --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (5 handlers)
[GIN-debug] POST /api/chat --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (5 handlers)
[GIN-debug] POST /api/embed --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (5 handlers)
[GIN-debug] POST /api/embeddings --> github.com/ollama/ollama/server.(*Server).EmbeddingsHandler-fm (5 handlers)
[GIN-debug] POST /v1/chat/completions --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (6 handlers)
[GIN-debug] POST /v1/completions --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (6 handlers)
[GIN-debug] POST /v1/embeddings --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (6 handlers)
[GIN-debug] GET /v1/models --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (6 handlers)
[GIN-debug] GET /v1/models/:model --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (6 handlers)
time=2025-08-25T10:55:07.933+08:00 level=INFO source=routes.go:1288 msg="Listening on 127.0.0.1:11434 (version 0.9.3)"
time=2025-08-25T10:55:07.933+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-08-25T10:55:07.935+08:00 level=INFO source=gpu.go:218 msg="using Intel GPU"
time=2025-08-25T10:55:07.935+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-08-25T10:55:07.935+08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-08-25T10:55:07.935+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=10 efficiency=4 threads=16
time=2025-08-25T10:55:07.965+08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="15.7 GiB" available="7.9 GiB"
[GIN] 2025/08/25 - 10:55:37 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/08/25 - 10:55:37 | 200 | 113.7179ms | 127.0.0.1 | POST "/api/show"
time=2025-08-25T10:55:37.564+08:00 level=INFO source=server.go:135 msg="system memory" total="15.7 GiB" free="7.8 GiB" free_swap="16.1 GiB"
time=2025-08-25T10:55:37.564+08:00 level=INFO source=server.go:187 msg=offload library=cpu layers.requested=-1 layers.model=29 layers.offload=0 layers.split="" memory.available="[7.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="4.7 GiB" memory.required.partial="0 B" memory.required.kv="224.0 MiB" memory.required.allocations="[4.7 GiB]" memory.weights.total="4.1 GiB" memory.weights.repeating="3.7 GiB" memory.weights.nonrepeating="426.4 MiB" memory.graph.full="304.0 MiB" memory.graph.partial="730.4 MiB"
get_memory_info: [warning] ext_intel_free_memory is not supported (export/set ZES_ENABLE_SYSMAN=1 to support), use total memory as free memory
llama_model_load_from_file_impl: using device SYCL0 (Intel(R) UHD Graphics 730) - 7096 MiB free
llama_model_loader: loaded meta data with 26 key-value pairs and 339 tensors from D:\models\blobs\sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 (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 = qwen2
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = DeepSeek R1 Distill Qwen 7B
llama_model_loader: - kv 3: general.basename str = DeepSeek-R1-Distill-Qwen
llama_model_loader: - kv 4: general.size_label str = 7B
llama_model_loader: - kv 5: qwen2.block_count u32 = 28
llama_model_loader: - kv 6: qwen2.context_length u32 = 131072
llama_model_loader: - kv 7: qwen2.embedding_length u32 = 3584
llama_model_loader: - kv 8: qwen2.feed_forward_length u32 = 18944
llama_model_loader: - kv 9: qwen2.attention.head_count u32 = 28
llama_model_loader: - kv 10: qwen2.attention.head_count_kv u32 = 4
llama_model_loader: - kv 11: qwen2.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 12: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 13: general.file_type u32 = 15
llama_model_loader: - kv 14: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 15: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 18: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 151646
llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 151643
llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 24: tokenizer.chat_template str = {% if not add_generation_prompt is de...
llama_model_loader: - kv 25: general.quantization_version u32 = 2
llama_model_loader: - type f32: 141 tensors
llama_model_loader: - type q4_K: 169 tensors
llama_model_loader: - type q6_K: 29 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 4.36 GiB (4.91 BPW)
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 22
load: token to piece cache size = 0.9310 MB
print_info: arch = qwen2
print_info: vocab_only = 1
print_info: model type = ?B
print_info: model params = 7.62 B
print_info: general.name = DeepSeek R1 Distill Qwen 7B
print_info: vocab type = BPE
print_info: n_vocab = 152064
print_info: n_merges = 151387
print_info: BOS token = 151646 '<｜begin▁of▁sentence｜>'
print_info: EOS token = 151643 '<｜end▁of▁sentence｜>'
print_info: EOT token = 151643 '<｜end▁of▁sentence｜>'
print_info: PAD token = 151643 '<｜end▁of▁sentence｜>'
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 '<｜end▁of▁sentence｜>'
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=2025-08-25T10:55:38.215+08:00 level=INFO source=server.go:458 msg="starting llama server" cmd="C:\\Users\\qinhw\\AppData\\Local\\Programs\\miniconda3\\envs\\ipex-llm\\Lib\\site-packages\\bigdl\\cpp\\libs\\ollama\\ollama-lib.exe runner --model D:\\models\\blobs\\sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 --ctx-size 4096 --batch-size 512 --n-gpu-layers 999 --threads 6 --no-mmap --parallel 2 --port 63262"
time=2025-08-25T10:55:38.392+08:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
time=2025-08-25T10:55:38.394+08:00 level=INFO source=server.go:618 msg="waiting for llama runner to start responding"
time=2025-08-25T10:55:38.396+08:00 level=INFO source=server.go:652 msg="waiting for server to become available" status="llm server error"
time=2025-08-25T10:55:38.603+08:00 level=INFO source=runner.go:851 msg="starting go runner"
time=2025-08-25T10:55:38.627+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(clang)
time=2025-08-25T10:55:38.629+08:00 level=INFO source=runner.go:911 msg="Server listening on 127.0.0.1:63262"
time=2025-08-25T10:55:38.647+08:00 level=INFO source=server.go:652 msg="waiting for server to become available" status="llm server loading model"
get_memory_info: [warning] ext_intel_free_memory is not supported (export/set ZES_ENABLE_SYSMAN=1 to support), use total memory as free memory
llama_model_load_from_file_impl: using device SYCL0 (Intel(R) UHD Graphics 730) - 7096 MiB free
llama_model_loader: loaded meta data with 26 key-value pairs and 339 tensors from D:\models\blobs\sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 (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 = qwen2
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = DeepSeek R1 Distill Qwen 7B
llama_model_loader: - kv 3: general.basename str = DeepSeek-R1-Distill-Qwen
llama_model_loader: - kv 4: general.size_label str = 7B
llama_model_loader: - kv 5: qwen2.block_count u32 = 28
llama_model_loader: - kv 6: qwen2.context_length u32 = 131072
llama_model_loader: - kv 7: qwen2.embedding_length u32 = 3584
llama_model_loader: - kv 8: qwen2.feed_forward_length u32 = 18944
llama_model_loader: - kv 9: qwen2.attention.head_count u32 = 28
llama_model_loader: - kv 10: qwen2.attention.head_count_kv u32 = 4
llama_model_loader: - kv 11: qwen2.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 12: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 13: general.file_type u32 = 15
llama_model_loader: - kv 14: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 15: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 18: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 151646
llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 151643
llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 24: tokenizer.chat_template str = {% if not add_generation_prompt is de...
llama_model_loader: - kv 25: general.quantization_version u32 = 2
llama_model_loader: - type f32: 141 tensors
llama_model_loader: - type q4_K: 169 tensors
llama_model_loader: - type q6_K: 29 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 4.36 GiB (4.91 BPW)
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 22
load: token to piece cache size = 0.9310 MB
print_info: arch = qwen2
print_info: vocab_only = 0
print_info: n_ctx_train = 131072
print_info: n_embd = 3584
print_info: n_layer = 28
print_info: n_head = 28
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 = 7
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_mSource: intel/ipex-llm