[GH-ISSUE #6003] AMD Radeon RX 6750 XT Support #3754

New Issue

GiteaMirror · 2026-04-12T14:33:56-05:00

GiteaMirror commented

2026-04-12 14:33:56 -05:00

Originally created by @SmollClover on GitHub (Jul 27, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6003

What is the issue?

Currently, as it seems, the Radeon RX 6750 XT isn't supported by Ollama and trying to force it to use it using env HSA_OVERRIDE_GFX_VERSION=gfx1031 ollama serve results in it being unable to initialize the tensile host.

Edit: Without the HSA_OVERRIDE_GFX_VERSION, it just states that it wasn't able to find a supported GPU.

Ollama Serve Logs

env HSA_OVERRIDE_GFX_VERSION=gfx1031 ollama serve     

2024/07/27 02:13:11 routes.go:1099: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION:gfx1031 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/name/.ollama/models 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://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-07-27T02:13:11.712+02:00 level=INFO source=images.go:784 msg="total blobs: 6"
time=2024-07-27T02:13:11.712+02:00 level=INFO source=images.go:791 msg="total unused blobs removed: 0"
time=2024-07-27T02:13:11.712+02:00 level=INFO source=routes.go:1146 msg="Listening on 127.0.0.1:11434 (version 0.3.0)"
time=2024-07-27T02:13:11.712+02:00 level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama924064373/runners
time=2024-07-27T02:13:14.557+02:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cuda_v11 rocm_v60102 cpu cpu_avx cpu_avx2]"
time=2024-07-27T02:13:14.557+02:00 level=INFO source=gpu.go:205 msg="looking for compatible GPUs"
time=2024-07-27T02:13:14.564+02:00 level=WARN source=amd_linux.go:58 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"
time=2024-07-27T02:13:14.567+02:00 level=INFO source=amd_linux.go:333 msg="skipping rocm gfx compatibility check" HSA_OVERRIDE_GFX_VERSION=gfx1031
time=2024-07-27T02:13:14.567+02:00 level=INFO source=types.go:105 msg="inference compute" id=0 library=rocm compute=gfx1031 driver=0.0 name=1002:73df total="12.0 GiB" available="10.6 GiB"
[GIN] 2024/07/27 - 02:13:30 | 200 |      29.188µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/07/27 - 02:13:30 | 200 |    15.59507ms |       127.0.0.1 | POST     "/api/show"
time=2024-07-27T02:13:30.912+02:00 level=INFO source=memory.go:309 msg="offload to rocm" layers.requested=-1 layers.model=81 layers.offload=18 layers.split="" memory.available="[10.6 GiB]" memory.required.full="39.3 GiB" memory.required.partial="10.2 GiB" memory.required.kv="640.0 MiB" memory.required.allocations="[10.2 GiB]" memory.weights.total="36.5 GiB" memory.weights.repeating="35.7 GiB" memory.weights.nonrepeating="822.0 MiB" memory.graph.full="324.0 MiB" memory.graph.partial="1.1 GiB"
time=2024-07-27T02:13:30.913+02:00 level=INFO source=server.go:383 msg="starting llama server" cmd="/tmp/ollama924064373/runners/rocm_v60102/ollama_llama_server --model /home/name/.ollama/models/blobs/sha256-9631a2551ac477921b64862e5cd4e13223183d7699ebf6bf6d14488edc8b4552 --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 18 --parallel 1 --port 46711"
time=2024-07-27T02:13:30.913+02:00 level=INFO source=sched.go:437 msg="loaded runners" count=1
time=2024-07-27T02:13:30.913+02:00 level=INFO source=server.go:583 msg="waiting for llama runner to start responding"
time=2024-07-27T02:13:30.918+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error"
INFO [main] build info | build=1 commit="d94c6e0" tid="139702802625344" timestamp=1722039211
INFO [main] system info | n_threads=8 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="139702802625344" timestamp=1722039211 total_threads=8
INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="7" port="46711" tid="139702802625344" timestamp=1722039211
llama_model_loader: loaded meta data with 22 key-value pairs and 723 tensors from /home/name/.ollama/models/blobs/sha256-9631a2551ac477921b64862e5cd4e13223183d7699ebf6bf6d14488edc8b4552 (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              = llama
llama_model_loader: - kv   1:                               general.name str              = dolphin-2.9-llama3-70b
llama_model_loader: - kv   2:                          llama.block_count u32              = 80
llama_model_loader: - kv   3:                       llama.context_length u32              = 8192
llama_model_loader: - kv   4:                     llama.embedding_length u32              = 8192
llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 28672
llama_model_loader: - kv   6:                 llama.attention.head_count u32              = 64
llama_model_loader: - kv   7:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv   8:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  10:                          general.file_type u32              = 2
llama_model_loader: - kv  11:                           llama.vocab_size u32              = 128258
llama_model_loader: - kv  12:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2
time=2024-07-27T02:13:31.221+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server loading model"
llama_model_loader: - kv  14:                      tokenizer.ggml.tokens arr[str,128258]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr[i32,128258]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  16:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  17:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  18:                tokenizer.ggml.eos_token_id u32              = 128256
llama_model_loader: - kv  19:            tokenizer.ggml.padding_token_id u32              = 128001
llama_model_loader: - kv  20:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
llama_model_loader: - kv  21:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  161 tensors
llama_model_loader: - type q4_0:  561 tensors
llama_model_loader: - type q6_K:    1 tensors
llm_load_vocab: missing or unrecognized pre-tokenizer type, using: 'default'
llm_load_vocab: special tokens cache size = 258
llm_load_vocab: token to piece cache size = 0.8000 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 128258
llm_load_print_meta: n_merges         = 280147
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 8192
llm_load_print_meta: n_embd           = 8192
llm_load_print_meta: n_layer          = 80
llm_load_print_meta: n_head           = 64
llm_load_print_meta: n_head_kv        = 8
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_swa            = 0
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 8
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-05
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             = 28672
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        = 0
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 8192
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       = 70B
llm_load_print_meta: model ftype      = Q4_0
llm_load_print_meta: model params     = 70.55 B
llm_load_print_meta: model size       = 37.22 GiB (4.53 BPW) 
llm_load_print_meta: general.name     = dolphin-2.9-llama3-70b
llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token        = 128256 '<|im_end|>'
llm_load_print_meta: PAD token        = 128001 '<|end_of_text|>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOT token        = 128256 '<|im_end|>'
llm_load_print_meta: max token length = 256
/opt/amdgpu/share/libdrm/amdgpu.ids: No such file or directory

rocBLAS error: Could not initialize Tensile host: No devices found
time=2024-07-27T02:13:32.174+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server not responding"
time=2024-07-27T02:13:32.563+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error"
time=2024-07-27T02:13:32.813+02:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: error:Could not initialize Tensile host: No devices found"

ROCMInfo

ROCk module is loaded
=====================    
HSA System Attributes    
=====================    
Runtime Version:         1.13
Runtime Ext Version:     1.4
System Timestamp Freq.:  1000.000000MHz
Sig. Max Wait Duration:  18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count)
Machine Model:           LARGE                              
System Endianness:       LITTLE                             
Mwaitx:                  DISABLED
DMAbuf Support:          YES

==========               
HSA Agents               
==========               
*******                  
Agent 1                  
*******                  
  Name:                    Intel(R) Core(TM) i7-9700 CPU @ 3.00GHz
  Uuid:                    CPU-XX                             
  Marketing Name:          Intel(R) Core(TM) i7-9700 CPU @ 3.00GHz
  Vendor Name:             CPU                                
  Feature:                 None specified                     
  Profile:                 FULL_PROFILE                       
  Float Round Mode:        NEAR                               
  Max Queue Number:        0(0x0)                             
  Queue Min Size:          0(0x0)                             
  Queue Max Size:          0(0x0)                             
  Queue Type:              MULTI                              
  Node:                    0                                  
  Device Type:             CPU                                
  Cache Info:              
    L1:                      32768(0x8000) KB                   
  Chip ID:                 0(0x0)                             
  ASIC Revision:           0(0x0)                             
  Cacheline Size:          64(0x40)                           
  Max Clock Freq. (MHz):   4700                               
  BDFID:                   0                                  
  Internal Node ID:        0                                  
  Compute Unit:            8                                  
  SIMDs per CU:            0                                  
  Shader Engines:          0                                  
  Shader Arrs. per Eng.:   0                                  
  WatchPts on Addr. Ranges:1                                  
  Features:                None
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: FINE GRAINED        
      Size:                    65746152(0x3eb34e8) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 2                   
      Segment:                 GLOBAL; FLAGS: KERNARG, FINE GRAINED
      Size:                    65746152(0x3eb34e8) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 3                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    65746152(0x3eb34e8) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
  ISA Info:                
*******                  
Agent 2                  
*******                  
  Name:                    gfx1031                            
  Uuid:                    GPU-XX                             
  Marketing Name:          AMD Radeon RX 6750 XT              
  Vendor Name:             AMD                                
  Feature:                 KERNEL_DISPATCH                    
  Profile:                 BASE_PROFILE                       
  Float Round Mode:        NEAR                               
  Max Queue Number:        128(0x80)                          
  Queue Min Size:          64(0x40)                           
  Queue Max Size:          131072(0x20000)                    
  Queue Type:              MULTI                              
  Node:                    1                                  
  Device Type:             GPU                                
  Cache Info:              
    L1:                      16(0x10) KB                        
    L2:                      3072(0xc00) KB                     
    L3:                      98304(0x18000) KB                  
  Chip ID:                 29663(0x73df)                      
  ASIC Revision:           0(0x0)                             
  Cacheline Size:          64(0x40)                           
  Max Clock Freq. (MHz):   2880                               
  BDFID:                   768                                
  Internal Node ID:        1                                  
  Compute Unit:            40                                 
  SIMDs per CU:            2                                  
  Shader Engines:          2                                  
  Shader Arrs. per Eng.:   2                                  
  WatchPts on Addr. Ranges:4                                  
  Coherent Host Access:    FALSE                              
  Features:                KERNEL_DISPATCH 
  Fast F16 Operation:      TRUE                               
  Wavefront Size:          32(0x20)                           
  Workgroup Max Size:      1024(0x400)                        
  Workgroup Max Size per Dimension:
    x                        1024(0x400)                        
    y                        1024(0x400)                        
    z                        1024(0x400)                        
  Max Waves Per CU:        32(0x20)                           
  Max Work-item Per CU:    1024(0x400)                        
  Grid Max Size:           4294967295(0xffffffff)             
  Grid Max Size per Dimension:
    x                        4294967295(0xffffffff)             
    y                        4294967295(0xffffffff)             
    z                        4294967295(0xffffffff)             
  Max fbarriers/Workgrp:   32                                 
  Packet Processor uCode:: 118                                
  SDMA engine uCode::      80                                 
  IOMMU Support::          None                               
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    12566528(0xbfc000) KB              
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:2048KB                             
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 2                   
      Segment:                 GLOBAL; FLAGS: EXTENDED FINE GRAINED
      Size:                    12566528(0xbfc000) KB              
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:2048KB                             
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 3                   
      Segment:                 GROUP                              
      Size:                    64(0x40) KB                        
      Allocatable:             FALSE                              
      Alloc Granule:           0KB                                
      Alloc Recommended Granule:0KB                                
      Alloc Alignment:         0KB                                
      Accessible by all:       FALSE                              
  ISA Info:                
    ISA 1                    
      Name:                    amdgcn-amd-amdhsa--gfx1031         
      Machine Models:          HSA_MACHINE_MODEL_LARGE            
      Profiles:                HSA_PROFILE_BASE                   
      Default Rounding Mode:   NEAR                               
      Default Rounding Mode:   NEAR                               
      Fast f16:                TRUE                               
      Workgroup Max Size:      1024(0x400)                        
      Workgroup Max Size per Dimension:
        x                        1024(0x400)                        
        y                        1024(0x400)                        
        z                        1024(0x400)                        
      Grid Max Size:           4294967295(0xffffffff)             
      Grid Max Size per Dimension:
        x                        4294967295(0xffffffff)             
        y                        4294967295(0xffffffff)             
        z                        4294967295(0xffffffff)             
      FBarrier Max Size:       32                                 
*** Done ***

OS

Linux

GPU

AMD

CPU

Intel

Ollama version

0.3.0

Originally created by @SmollClover on GitHub (Jul 27, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6003 ### What is the issue? Currently, as it seems, the Radeon RX 6750 XT isn't supported by Ollama and trying to force it to use it using `env HSA_OVERRIDE_GFX_VERSION=gfx1031 ollama serve` results in it being unable to initialize the tensile host. Edit: Without the HSA_OVERRIDE_GFX_VERSION, it just states that it wasn't able to find a supported GPU. <details> <summary>Ollama Serve Logs</summary> ``` env HSA_OVERRIDE_GFX_VERSION=gfx1031 ollama serve 2024/07/27 02:13:11 routes.go:1099: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION:gfx1031 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/name/.ollama/models 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://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-07-27T02:13:11.712+02:00 level=INFO source=images.go:784 msg="total blobs: 6" time=2024-07-27T02:13:11.712+02:00 level=INFO source=images.go:791 msg="total unused blobs removed: 0" time=2024-07-27T02:13:11.712+02:00 level=INFO source=routes.go:1146 msg="Listening on 127.0.0.1:11434 (version 0.3.0)" time=2024-07-27T02:13:11.712+02:00 level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama924064373/runners time=2024-07-27T02:13:14.557+02:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cuda_v11 rocm_v60102 cpu cpu_avx cpu_avx2]" time=2024-07-27T02:13:14.557+02:00 level=INFO source=gpu.go:205 msg="looking for compatible GPUs" time=2024-07-27T02:13:14.564+02:00 level=WARN source=amd_linux.go:58 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory" time=2024-07-27T02:13:14.567+02:00 level=INFO source=amd_linux.go:333 msg="skipping rocm gfx compatibility check" HSA_OVERRIDE_GFX_VERSION=gfx1031 time=2024-07-27T02:13:14.567+02:00 level=INFO source=types.go:105 msg="inference compute" id=0 library=rocm compute=gfx1031 driver=0.0 name=1002:73df total="12.0 GiB" available="10.6 GiB" [GIN] 2024/07/27 - 02:13:30 | 200 | 29.188µs | 127.0.0.1 | HEAD "/" [GIN] 2024/07/27 - 02:13:30 | 200 | 15.59507ms | 127.0.0.1 | POST "/api/show" time=2024-07-27T02:13:30.912+02:00 level=INFO source=memory.go:309 msg="offload to rocm" layers.requested=-1 layers.model=81 layers.offload=18 layers.split="" memory.available="[10.6 GiB]" memory.required.full="39.3 GiB" memory.required.partial="10.2 GiB" memory.required.kv="640.0 MiB" memory.required.allocations="[10.2 GiB]" memory.weights.total="36.5 GiB" memory.weights.repeating="35.7 GiB" memory.weights.nonrepeating="822.0 MiB" memory.graph.full="324.0 MiB" memory.graph.partial="1.1 GiB" time=2024-07-27T02:13:30.913+02:00 level=INFO source=server.go:383 msg="starting llama server" cmd="/tmp/ollama924064373/runners/rocm_v60102/ollama_llama_server --model /home/name/.ollama/models/blobs/sha256-9631a2551ac477921b64862e5cd4e13223183d7699ebf6bf6d14488edc8b4552 --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 18 --parallel 1 --port 46711" time=2024-07-27T02:13:30.913+02:00 level=INFO source=sched.go:437 msg="loaded runners" count=1 time=2024-07-27T02:13:30.913+02:00 level=INFO source=server.go:583 msg="waiting for llama runner to start responding" time=2024-07-27T02:13:30.918+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error" INFO [main] build info | build=1 commit="d94c6e0" tid="139702802625344" timestamp=1722039211 INFO [main] system info | n_threads=8 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="139702802625344" timestamp=1722039211 total_threads=8 INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="7" port="46711" tid="139702802625344" timestamp=1722039211 llama_model_loader: loaded meta data with 22 key-value pairs and 723 tensors from /home/name/.ollama/models/blobs/sha256-9631a2551ac477921b64862e5cd4e13223183d7699ebf6bf6d14488edc8b4552 (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 = llama llama_model_loader: - kv 1: general.name str = dolphin-2.9-llama3-70b llama_model_loader: - kv 2: llama.block_count u32 = 80 llama_model_loader: - kv 3: llama.context_length u32 = 8192 llama_model_loader: - kv 4: llama.embedding_length u32 = 8192 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 28672 llama_model_loader: - kv 6: llama.attention.head_count u32 = 64 llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 8: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: general.file_type u32 = 2 llama_model_loader: - kv 11: llama.vocab_size u32 = 128258 llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2 time=2024-07-27T02:13:31.221+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server loading model" llama_model_loader: - kv 14: tokenizer.ggml.tokens arr[str,128258] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,128258] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 16: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 128256 llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 128001 llama_model_loader: - kv 20: tokenizer.chat_template str = {% if not add_generation_prompt is de... llama_model_loader: - kv 21: general.quantization_version u32 = 2 llama_model_loader: - type f32: 161 tensors llama_model_loader: - type q4_0: 561 tensors llama_model_loader: - type q6_K: 1 tensors llm_load_vocab: missing or unrecognized pre-tokenizer type, using: 'default' llm_load_vocab: special tokens cache size = 258 llm_load_vocab: token to piece cache size = 0.8000 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128258 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 8192 llm_load_print_meta: n_embd = 8192 llm_load_print_meta: n_layer = 80 llm_load_print_meta: n_head = 64 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 8 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-05 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 = 28672 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 = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 8192 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 = 70B llm_load_print_meta: model ftype = Q4_0 llm_load_print_meta: model params = 70.55 B llm_load_print_meta: model size = 37.22 GiB (4.53 BPW) llm_load_print_meta: general.name = dolphin-2.9-llama3-70b llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128256 '<|im_end|>' llm_load_print_meta: PAD token = 128001 '<|end_of_text|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128256 '<|im_end|>' llm_load_print_meta: max token length = 256 /opt/amdgpu/share/libdrm/amdgpu.ids: No such file or directory rocBLAS error: Could not initialize Tensile host: No devices found time=2024-07-27T02:13:32.174+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server not responding" time=2024-07-27T02:13:32.563+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error" time=2024-07-27T02:13:32.813+02:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: error:Could not initialize Tensile host: No devices found" ``` </details> <details> <summary>ROCMInfo</summary> ``` ROCk module is loaded ===================== HSA System Attributes ===================== Runtime Version: 1.13 Runtime Ext Version: 1.4 System Timestamp Freq.: 1000.000000MHz Sig. Max Wait Duration: 18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count) Machine Model: LARGE System Endianness: LITTLE Mwaitx: DISABLED DMAbuf Support: YES ========== HSA Agents ========== ******* Agent 1 ******* Name: Intel(R) Core(TM) i7-9700 CPU @ 3.00GHz Uuid: CPU-XX Marketing Name: Intel(R) Core(TM) i7-9700 CPU @ 3.00GHz Vendor Name: CPU Feature: None specified Profile: FULL_PROFILE Float Round Mode: NEAR Max Queue Number: 0(0x0) Queue Min Size: 0(0x0) Queue Max Size: 0(0x0) Queue Type: MULTI Node: 0 Device Type: CPU Cache Info: L1: 32768(0x8000) KB Chip ID: 0(0x0) ASIC Revision: 0(0x0) Cacheline Size: 64(0x40) Max Clock Freq. (MHz): 4700 BDFID: 0 Internal Node ID: 0 Compute Unit: 8 SIMDs per CU: 0 Shader Engines: 0 Shader Arrs. per Eng.: 0 WatchPts on Addr. Ranges:1 Features: None Pool Info: Pool 1 Segment: GLOBAL; FLAGS: FINE GRAINED Size: 65746152(0x3eb34e8) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:4KB Alloc Alignment: 4KB Accessible by all: TRUE Pool 2 Segment: GLOBAL; FLAGS: KERNARG, FINE GRAINED Size: 65746152(0x3eb34e8) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:4KB Alloc Alignment: 4KB Accessible by all: TRUE Pool 3 Segment: GLOBAL; FLAGS: COARSE GRAINED Size: 65746152(0x3eb34e8) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:4KB Alloc Alignment: 4KB Accessible by all: TRUE ISA Info: ******* Agent 2 ******* Name: gfx1031 Uuid: GPU-XX Marketing Name: AMD Radeon RX 6750 XT Vendor Name: AMD Feature: KERNEL_DISPATCH Profile: BASE_PROFILE Float Round Mode: NEAR Max Queue Number: 128(0x80) Queue Min Size: 64(0x40) Queue Max Size: 131072(0x20000) Queue Type: MULTI Node: 1 Device Type: GPU Cache Info: L1: 16(0x10) KB L2: 3072(0xc00) KB L3: 98304(0x18000) KB Chip ID: 29663(0x73df) ASIC Revision: 0(0x0) Cacheline Size: 64(0x40) Max Clock Freq. (MHz): 2880 BDFID: 768 Internal Node ID: 1 Compute Unit: 40 SIMDs per CU: 2 Shader Engines: 2 Shader Arrs. per Eng.: 2 WatchPts on Addr. Ranges:4 Coherent Host Access: FALSE Features: KERNEL_DISPATCH Fast F16 Operation: TRUE Wavefront Size: 32(0x20) Workgroup Max Size: 1024(0x400) Workgroup Max Size per Dimension: x 1024(0x400) y 1024(0x400) z 1024(0x400) Max Waves Per CU: 32(0x20) Max Work-item Per CU: 1024(0x400) Grid Max Size: 4294967295(0xffffffff) Grid Max Size per Dimension: x 4294967295(0xffffffff) y 4294967295(0xffffffff) z 4294967295(0xffffffff) Max fbarriers/Workgrp: 32 Packet Processor uCode:: 118 SDMA engine uCode:: 80 IOMMU Support:: None Pool Info: Pool 1 Segment: GLOBAL; FLAGS: COARSE GRAINED Size: 12566528(0xbfc000) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:2048KB Alloc Alignment: 4KB Accessible by all: FALSE Pool 2 Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED Size: 12566528(0xbfc000) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:2048KB Alloc Alignment: 4KB Accessible by all: FALSE Pool 3 Segment: GROUP Size: 64(0x40) KB Allocatable: FALSE Alloc Granule: 0KB Alloc Recommended Granule:0KB Alloc Alignment: 0KB Accessible by all: FALSE ISA Info: ISA 1 Name: amdgcn-amd-amdhsa--gfx1031 Machine Models: HSA_MACHINE_MODEL_LARGE Profiles: HSA_PROFILE_BASE Default Rounding Mode: NEAR Default Rounding Mode: NEAR Fast f16: TRUE Workgroup Max Size: 1024(0x400) Workgroup Max Size per Dimension: x 1024(0x400) y 1024(0x400) z 1024(0x400) Grid Max Size: 4294967295(0xffffffff) Grid Max Size per Dimension: x 4294967295(0xffffffff) y 4294967295(0xffffffff) z 4294967295(0xffffffff) FBarrier Max Size: 32 *** Done *** ``` </details> ### OS Linux ### GPU AMD ### CPU Intel ### Ollama version 0.3.0

GiteaMirror added the bug label 2026-04-12 14:33:56 -05:00

GiteaMirror closed this issue

2026-04-12 14:33:57 -05:00

GiteaMirror commented

2026-04-12 14:33:58 -05:00

@likelovewant commented on GitHub (Jul 28, 2024):

Try set value HSA_OVERRIDE_GFX_VERSION=gfx1030. gfx1031 don't support both by rocm and ollama. But support gfx1030

@likelovewant commented on GitHub (Jul 28, 2024): Try set value HSA_OVERRIDE_GFX_VERSION=gfx1030. gfx1031 don't support both by rocm and ollama. But support gfx1030

GiteaMirror commented

2026-04-12 14:33:58 -05:00

@SmollClover commented on GitHub (Jul 28, 2024):

When setting it to gfx1030, it seems to be unable to verify the rocm library even though I have rocm installed through the nobara provided driver manager.

time=2024-07-28T14:15:16.257+02:00 level=INFO source=images.go:784 msg="total blobs: 0"
time=2024-07-28T14:15:16.257+02:00 level=INFO source=images.go:791 msg="total unused blobs removed: 0"
time=2024-07-28T14:15:16.257+02:00 level=INFO source=routes.go:1146 msg="Listening on 127.0.0.1:11434 (version 0.3.0)"
time=2024-07-28T14:15:16.257+02:00 level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama1804859112/runners
time=2024-07-28T14:15:19.048+02:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11 rocm_v60102]"
time=2024-07-28T14:15:19.048+02:00 level=INFO source=gpu.go:205 msg="looking for compatible GPUs"
time=2024-07-28T14:15:19.055+02:00 level=WARN source=amd_linux.go:58 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"
time=2024-07-28T14:15:19.057+02:00 level=WARN source=amd_linux.go:380 msg="amdgpu detected, but no compatible rocm library found.  Either install rocm v6, or follow manual install instructions at https://github.com/ollama/ollama/blob/main/docs/linux.md#manual-install"
time=2024-07-28T14:15:19.057+02:00 level=WARN source=amd_linux.go:307 msg="unable to verify rocm library, will use cpu" error="no suitable rocm found, falling back to CPU"
time=2024-07-28T14:15:19.057+02:00 level=INFO source=gpu.go:346 msg="no compatible GPUs were discovered"
time=2024-07-28T14:15:19.057+02:00 level=INFO source=types.go:105 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="62.7 GiB" available="55.6 GiB"

@SmollClover commented on GitHub (Jul 28, 2024): When setting it to gfx1030, it seems to be unable to verify the rocm library even though I have rocm installed through the nobara provided driver manager. ``` time=2024-07-28T14:15:16.257+02:00 level=INFO source=images.go:784 msg="total blobs: 0" time=2024-07-28T14:15:16.257+02:00 level=INFO source=images.go:791 msg="total unused blobs removed: 0" time=2024-07-28T14:15:16.257+02:00 level=INFO source=routes.go:1146 msg="Listening on 127.0.0.1:11434 (version 0.3.0)" time=2024-07-28T14:15:16.257+02:00 level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama1804859112/runners time=2024-07-28T14:15:19.048+02:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11 rocm_v60102]" time=2024-07-28T14:15:19.048+02:00 level=INFO source=gpu.go:205 msg="looking for compatible GPUs" time=2024-07-28T14:15:19.055+02:00 level=WARN source=amd_linux.go:58 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory" time=2024-07-28T14:15:19.057+02:00 level=WARN source=amd_linux.go:380 msg="amdgpu detected, but no compatible rocm library found. Either install rocm v6, or follow manual install instructions at https://github.com/ollama/ollama/blob/main/docs/linux.md#manual-install" time=2024-07-28T14:15:19.057+02:00 level=WARN source=amd_linux.go:307 msg="unable to verify rocm library, will use cpu" error="no suitable rocm found, falling back to CPU" time=2024-07-28T14:15:19.057+02:00 level=INFO source=gpu.go:346 msg="no compatible GPUs were discovered" time=2024-07-28T14:15:19.057+02:00 level=INFO source=types.go:105 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="62.7 GiB" available="55.6 GiB" ```

GiteaMirror commented

2026-04-12 14:33:59 -05:00

@likelovewant commented on GitHub (Jul 28, 2024):

Follow the doc guide and do necessary changes.or as guide here https://github.com/ollama/ollama/issues/3037#issuecomment-1987672631
. Sometimes, restart the ollama serve will helps

@likelovewant commented on GitHub (Jul 28, 2024): Follow the doc guide and do necessary changes.or as guide here https://github.com/ollama/ollama/issues/3037#issuecomment-1987672631 . Sometimes, restart the ollama serve will helps

GiteaMirror commented

2026-04-12 14:34:00 -05:00

@SmollClover commented on GitHub (Jul 28, 2024):

Using gfx1030 makes no difference for me and behaves the same as when I tried gfx1031.

Jul 28 15:09:47 desktop ollama[8549]: rocBLAS error: Could not initialize Tensile host: No devices found
Jul 28 15:09:47 desktop ollama[8549]: time=2024-07-28T15:09:47.962+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server not responding"
Jul 28 15:09:48 desktop ollama[8549]: time=2024-07-28T15:09:48.353+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error"
Jul 28 15:09:48 desktop ollama[8549]: time=2024-07-28T15:09:48.604+02:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: error:Could not initialize Tensile host: No devices found"

@SmollClover commented on GitHub (Jul 28, 2024): Using gfx1030 makes no difference for me and behaves the same as when I tried gfx1031. ``` Jul 28 15:09:47 desktop ollama[8549]: rocBLAS error: Could not initialize Tensile host: No devices found Jul 28 15:09:47 desktop ollama[8549]: time=2024-07-28T15:09:47.962+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server not responding" Jul 28 15:09:48 desktop ollama[8549]: time=2024-07-28T15:09:48.353+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error" Jul 28 15:09:48 desktop ollama[8549]: time=2024-07-28T15:09:48.604+02:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: error:Could not initialize Tensile host: No devices found" ```

GiteaMirror commented

2026-04-12 14:34:00 -05:00

@likelovewant commented on GitHub (Jul 28, 2024):

Using gfx1030 makes no difference for me and behaves the same as when I tried gfx1031.


Jul 28 15:09:47 desktop ollama[8549]: rocBLAS error: Could not initialize Tensile host: No devices found

Jul 28 15:09:47 desktop ollama[8549]: time=2024-07-28T15:09:47.962+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server not responding"

Jul 28 15:09:48 desktop ollama[8549]: time=2024-07-28T15:09:48.353+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error"

Jul 28 15:09:48 desktop ollama[8549]: time=2024-07-28T15:09:48.604+02:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: error:Could not initialize Tensile host: No devices found"

It's almost ready to loading the tensile library . If everything set all right . Reboot is helps.

Or you could search helps from closed issues.

For example:

Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0"
Environment="AMD_SERIALIZE_KERNEL=3"
Environment="OLLAMA_LLM_LIBRARY=rocm_v60002" (this may need to change according to your version of ollama , could be found in the ollama program default folder , change the name accordingly)

@likelovewant commented on GitHub (Jul 28, 2024): > Using gfx1030 makes no difference for me and behaves the same as when I tried gfx1031. > > > > ``` > > Jul 28 15:09:47 desktop ollama[8549]: rocBLAS error: Could not initialize Tensile host: No devices found > > Jul 28 15:09:47 desktop ollama[8549]: time=2024-07-28T15:09:47.962+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server not responding" > > Jul 28 15:09:48 desktop ollama[8549]: time=2024-07-28T15:09:48.353+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error" > > Jul 28 15:09:48 desktop ollama[8549]: time=2024-07-28T15:09:48.604+02:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: error:Could not initialize Tensile host: No devices found" > > ``` It's almost ready to loading the tensile library . If everything set all right . Reboot is helps. Or you could search helps from closed issues. For example: Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0" Environment="AMD_SERIALIZE_KERNEL=3" Environment="OLLAMA_LLM_LIBRARY=rocm_v60002" (this may need to change according to your version of ollama , could be found in the ollama program default folder , change the name accordingly)

GiteaMirror commented

2026-04-12 14:34:00 -05:00

@SmollClover commented on GitHub (Jul 28, 2024):

Using gfx1030 makes no difference for me and behaves the same as when I tried gfx1031.
Jul 28 15:09:47 desktop ollama[8549]: rocBLAS error: Could not initialize Tensile host: No devices found

Jul 28 15:09:47 desktop ollama[8549]: time=2024-07-28T15:09:47.962+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server not responding"

Jul 28 15:09:48 desktop ollama[8549]: time=2024-07-28T15:09:48.353+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error"

Jul 28 15:09:48 desktop ollama[8549]: time=2024-07-28T15:09:48.604+02:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: error:Could not initialize Tensile host: No devices found"
It's almost ready to loading the tensile library . If everything set all right . Reboot is helps.

Or you could search helps from closed issues.

For example:

Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0"
Environment="AMD_SERIALIZE_KERNEL=3"
Environment="OLLAMA_LLM_LIBRARY=rocm_v60002" (this may need to change according to your version of ollama , could be found in the ollama program default folder , change the name accordingly)

Seems like it's finally also utilizing my GPU as reported by ollama ps with it reporting 73%/27% CPU/GPU. In case anyone in curious, below are the Environment variables I have now set in my ollama.service.

Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0"
Environment="AMD_SERIALIZE_KERNEL=3"
Environment="OLLAMA_LLM_LIBRARY=rocm_v60102"

@SmollClover commented on GitHub (Jul 28, 2024): > > Using gfx1030 makes no difference for me and behaves the same as when I tried gfx1031. > > ``` > > > > Jul 28 15:09:47 desktop ollama[8549]: rocBLAS error: Could not initialize Tensile host: No devices found > > > > Jul 28 15:09:47 desktop ollama[8549]: time=2024-07-28T15:09:47.962+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server not responding" > > > > Jul 28 15:09:48 desktop ollama[8549]: time=2024-07-28T15:09:48.353+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error" > > > > Jul 28 15:09:48 desktop ollama[8549]: time=2024-07-28T15:09:48.604+02:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: error:Could not initialize Tensile host: No devices found" > > ``` > > It's almost ready to loading the tensile library . If everything set all right . Reboot is helps. > > Or you could search helps from closed issues. > > For example: > > Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0" > Environment="AMD_SERIALIZE_KERNEL=3" > Environment="OLLAMA_LLM_LIBRARY=rocm_v60002" (this may need to change according to your version of ollama , could be found in the ollama program default folder , change the name accordingly) Seems like it's finally also utilizing my GPU as reported by `ollama ps` with it reporting `73%/27% CPU/GPU`. In case anyone in curious, below are the Environment variables I have now set in my ollama.service. ``` Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0" Environment="AMD_SERIALIZE_KERNEL=3" Environment="OLLAMA_LLM_LIBRARY=rocm_v60102" ```

GiteaMirror commented

2026-04-12 14:34:01 -05:00

@jcleng commented on GitHub (Mar 12, 2026):

🚀 use docker-compose to run for 6750XT

  ollama_amd:
    container_name: ollama_amd
    image: rocm/dev-ubuntu-24.04:7.2-complete
    privileged: true
    network_mode: host
    environment:
      - OLLAMA_DEBUG=1
      - AMD_LOG_LEVEL=3
      # rocminfo | grep -E "gfx|Device Name"
      - HSA_OVERRIDE_GFX_VERSION=10.3.0
      - AMD_SERIALIZE_KERNEL=3
      - OLLAMA_LLM_LIBRARY=rocm
      - OLLAMA_HOST=0.0.0.0:11435
    devices:
      # ls /dev/dri/render*
      - /dev/kfd:/dev/kfd
      - /dev/dri:/dev/dri
    group_add:
      - "video"
      - "render"
    ipc: host
    cap_add:
      - SYS_PTRACE
    security_opt:
      - seccomp=unconfined
    volumes:
      - /home/jcleng/ollama/:/root/.ollama/
    tty: true
    command: bash

and in container to download last ollama

# v0.17.7
tar -xvf ollama-linux-amd64.tar -C /usr/local/
tar -xvf ollama-linux-amd64-rocm.tar -C /usr/local/

last run in container

ollama serve

@jcleng commented on GitHub (Mar 12, 2026): 🚀 use docker-compose to run for 6750XT ```yml ollama_amd: container_name: ollama_amd image: rocm/dev-ubuntu-24.04:7.2-complete privileged: true network_mode: host environment: - OLLAMA_DEBUG=1 - AMD_LOG_LEVEL=3 # rocminfo | grep -E "gfx|Device Name" - HSA_OVERRIDE_GFX_VERSION=10.3.0 - AMD_SERIALIZE_KERNEL=3 - OLLAMA_LLM_LIBRARY=rocm - OLLAMA_HOST=0.0.0.0:11435 devices: # ls /dev/dri/render* - /dev/kfd:/dev/kfd - /dev/dri:/dev/dri group_add: - "video" - "render" ipc: host cap_add: - SYS_PTRACE security_opt: - seccomp=unconfined volumes: - /home/jcleng/ollama/:/root/.ollama/ tty: true command: bash ``` and in container to download last ollama ```shell # v0.17.7 tar -xvf ollama-linux-amd64.tar -C /usr/local/ tar -xvf ollama-linux-amd64-rocm.tar -C /usr/local/ ``` last run in container ```shell ollama serve ```

GiteaMirror commented

2026-04-12 14:34:02 -05:00

@eioo commented on GitHub (Apr 10, 2026):

Here's the full docker-compose.yml file that also updates to latest ollama.

services:
  ollama_amd:
    container_name: ollama_amd
    image: rocm/dev-ubuntu-24.04:7.2-complete
    privileged: true
    network_mode: host
    environment:
      - OLLAMA_DEBUG=1
      - AMD_LOG_LEVEL=3
      # rocminfo | grep -E "gfx|Device Name"
      - HSA_OVERRIDE_GFX_VERSION=10.3.0
      - AMD_SERIALIZE_KERNEL=3
      - OLLAMA_LLM_LIBRARY=rocm
      - OLLAMA_HOST=0.0.0.0:11435
    devices:
      # ls /dev/dri/render*
      - /dev/kfd:/dev/kfd
      - /dev/dri:/dev/dri
    group_add:
      - "video"
      - "render"
    ipc: host
    cap_add:
      - SYS_PTRACE
    security_opt:
      - seccomp=unconfined
    volumes:
      - /home/jcleng/ollama/:/root/.ollama/
    tty: true
    command: >
      bash -c '
        set -e
        echo "Installing curl and zst"
        apt update
        apt install -y zstd curl

        echo "Downloading latest ollama"
        curl -fsSL https://ollama.com/download/ollama-linux-amd64.tar.zst | tar x --zstd -C /usr
        echo "Downloading latest ollama-rocm"
        curl -fsSL https://ollama.com/download/ollama-linux-amd64-rocm.tar.zst | tar x --zstd -C /usr

        echo "Running ollama serve"
        ollama serve
      '

And then to run commands:

docker exec -it ollama_amd bash
ollama pull qwen3.5:2b

or call API directly:

curl http://localhost:11435/api/pull -d '{
  "name": "qwen3.5:2b"
}'

@eioo commented on GitHub (Apr 10, 2026): Here's the full `docker-compose.yml` file that also updates to latest ollama. ```yml services: ollama_amd: container_name: ollama_amd image: rocm/dev-ubuntu-24.04:7.2-complete privileged: true network_mode: host environment: - OLLAMA_DEBUG=1 - AMD_LOG_LEVEL=3 # rocminfo | grep -E "gfx|Device Name" - HSA_OVERRIDE_GFX_VERSION=10.3.0 - AMD_SERIALIZE_KERNEL=3 - OLLAMA_LLM_LIBRARY=rocm - OLLAMA_HOST=0.0.0.0:11435 devices: # ls /dev/dri/render* - /dev/kfd:/dev/kfd - /dev/dri:/dev/dri group_add: - "video" - "render" ipc: host cap_add: - SYS_PTRACE security_opt: - seccomp=unconfined volumes: - /home/jcleng/ollama/:/root/.ollama/ tty: true command: > bash -c ' set -e echo "Installing curl and zst" apt update apt install -y zstd curl echo "Downloading latest ollama" curl -fsSL https://ollama.com/download/ollama-linux-amd64.tar.zst | tar x --zstd -C /usr echo "Downloading latest ollama-rocm" curl -fsSL https://ollama.com/download/ollama-linux-amd64-rocm.tar.zst | tar x --zstd -C /usr echo "Running ollama serve" ollama serve ' ``` And then to run commands: ```sh docker exec -it ollama_amd bash ollama pull qwen3.5:2b ``` or call API directly: ```sh curl http://localhost:11435/api/pull -d '{ "name": "qwen3.5:2b" }' ```

GiteaMirror referenced this issue

2026-04-22 05:52:10 -05:00

[GH-ISSUE #3754] ollama rm Support deletion through ID #28076

GiteaMirror referenced this issue

2026-04-28 09:37:42 -05:00

[GH-ISSUE #3754] ollama rm Support deletion through ID #48828

GiteaMirror referenced this issue

2026-05-03 17:15:03 -05:00

[GH-ISSUE #3754] ollama rm Support deletion through ID #64354

GiteaMirror referenced this issue

2026-05-09 07:36:10 -05:00

[GH-ISSUE #3754] ollama rm Support deletion through ID #79995

Sign in to join this conversation.

Branches Tags

main

dhiltgen/llama-runner

parth-migrate-pi

codex/make-integration-hidden-and-lunchable

hoyyeva/migrate-pi

hoyyeva/opencode-thinking

hoyyeva/anthropic-local-image-path

parth-launch-codex-app

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

hoyyeva/qwen

parth/hide-claude-desktop-till-release

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#3754