github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.5k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #1430] coda error 222 after building #62798

New Issue
Closed
opened 2026-05-03 10:21:39 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-03 10:21:39 -05:00
Owner
Copy Link

Originally created by @rhettg on GitHub (Dec 8, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1430

Originally assigned to: @dhiltgen on GitHub.

This might be a llama.cpp question, but I'm struggling to get Ollama to work when I build it myself.

The release builds work fine for me:

$ sudo -u ollama /usr/bin/ollama serve
2023/12/07 17:52:41 images.go:779: total blobs: 10
2023/12/07 17:52:41 images.go:786: total unused blobs removed: 0
2023/12/07 17:52:41 routes.go:777: Listening on 127.0.0.1:11434 (version 0.1.11)
2023/12/07 17:53:08 llama.go:291: 9973 MB VRAM available, loading up to 60 GPU layers
2023/12/07 17:53:08 llama.go:420: starting llama runner
2023/12/07 17:53:08 llama.go:478: waiting for llama runner to start responding
ggml_init_cublas: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 3080, compute capability 8.6
{"timestamp":1702000389,"level":"INFO","function":"main","line":1323,"message":"build info","build":219,"commit":"9e70cc0"}
{"timestamp":1702000389,"level":"INFO","function":"main","line":1325,"message":"system info","n_threads":8,"n_threads_batch":-1,"total_threads":16,"system_info":"AVX = 1 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | "}

But when I build it, I see this:

CUDA error 222 at /home/rhettg/Projects/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:7003: the provided PTX was compiled with an unsupported toolchain.
current device: 0
2023/12/07 17:58:10 llama.go:441: 222 at /home/rhettg/Projects/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:7003: the provided PTX was compiled with an unsupported toolchain.
current device: 0
2023/12/07 17:58:10 llama.go:449: error starting llama runner: llama runner process has terminated
2023/12/07 17:58:10 llama.go:515: llama runner stopped successfully
More version details: 
$ git show HEAD
commit dd427f499a65b2357f6b47ab3eed62478f42397a (HEAD -> main, origin/main, origin/HEAD)
Merge: 2ae573c 02fe26c
Author: Matt Williams <m@technovangelist.com>
Date:   Thu Dec 7 14:42:24 2023 -0800

    Merge pull request #1419 from jmorganca/mattw/typescript-simplechat

    Simple chat example for typescript
$ nvidia-smi
Thu Dec  7 17:59:22 2023
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.129.03             Driver Version: 535.129.03   CUDA Version: 12.2     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  NVIDIA GeForce RTX 3080        Off | 00000000:2B:00.0  On |                  N/A |
|  0%   37C    P8              23W / 320W |      2MiB / 10240MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
|  No running processes found                                                           |
+---------------------------------------------------------------------------------------+
$ /usr/local/cuda/bin/nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Fri_Nov__3_17:16:49_PDT_2023
Cuda compilation tools, release 12.3, V12.3.103
Build cuda_12.3.r12.3/compiler.33492891_0
$ lsb_release -a
No LSB modules are available.
Distributor ID:	Ubuntu
Description:	Ubuntu 22.04.3 LTS
Release:	22.04
Codename:	jammy
$ dpkg -l | grep nvidia
ii  libnvidia-cfg1-535:amd64                   535.129.03-0ubuntu0.22.04.1             amd64        NVIDIA binary OpenGL/GLX configuration library
ii  libnvidia-common-535                       535.129.03-0ubuntu1                     all          Shared files used by the NVIDIA libraries
ii  libnvidia-compute-535:amd64                535.129.03-0ubuntu0.22.04.1             amd64        NVIDIA libcompute package
ii  libnvidia-compute-535:i386                 535.129.03-0ubuntu0.22.04.1             i386         NVIDIA libcompute package
ii  libnvidia-decode-535:amd64                 535.129.03-0ubuntu0.22.04.1             amd64        NVIDIA Video Decoding runtime libraries
ii  libnvidia-decode-535:i386                  535.129.03-0ubuntu0.22.04.1             i386         NVIDIA Video Decoding runtime libraries
ii  libnvidia-encode-535:amd64                 535.129.03-0ubuntu0.22.04.1             amd64        NVENC Video Encoding runtime library
ii  libnvidia-encode-535:i386                  535.129.03-0ubuntu0.22.04.1             i386         NVENC Video Encoding runtime library
ii  libnvidia-extra-535:amd64                  535.129.03-0ubuntu0.22.04.1             amd64        Extra libraries for the NVIDIA driver
ii  libnvidia-fbc1-535:amd64                   535.129.03-0ubuntu0.22.04.1             amd64        NVIDIA OpenGL-based Framebuffer Capture runtime library
ii  libnvidia-fbc1-535:i386                    535.129.03-0ubuntu0.22.04.1             i386         NVIDIA OpenGL-based Framebuffer Capture runtime library
ii  libnvidia-gl-535:amd64                     535.129.03-0ubuntu0.22.04.1             amd64        NVIDIA OpenGL/GLX/EGL/GLES GLVND libraries and Vulkan ICD
ii  libnvidia-gl-535:i386                      535.129.03-0ubuntu0.22.04.1             i386         NVIDIA OpenGL/GLX/EGL/GLES GLVND libraries and Vulkan ICD
rc  linux-modules-nvidia-535-6.2.0-26-generic  6.2.0-26.26~22.04.1+2                   amd64        Linux kernel nvidia modules for version 6.2.0-26
ii  linux-modules-nvidia-535-6.2.0-36-generic  6.2.0-36.37~22.04.1+1                   amd64        Linux kernel nvidia modules for version 6.2.0-36
ii  linux-modules-nvidia-535-6.2.0-37-generic  6.2.0-37.38~22.04.1                     amd64        Linux kernel nvidia modules for version 6.2.0-37
ii  linux-modules-nvidia-535-generic-hwe-22.04 6.2.0-37.38~22.04.1                     amd64        Extra drivers for nvidia-535 for the generic-hwe-22.04 flavour
rc  linux-objects-nvidia-535-6.2.0-26-generic  6.2.0-26.26~22.04.1+2                   amd64        Linux kernel nvidia modules for version 6.2.0-26 (objects)
ii  linux-objects-nvidia-535-6.2.0-36-generic  6.2.0-36.37~22.04.1+1                   amd64        Linux kernel nvidia modules for version 6.2.0-36 (objects)
ii  linux-objects-nvidia-535-6.2.0-37-generic  6.2.0-37.38~22.04.1                     amd64        Linux kernel nvidia modules for version 6.2.0-37 (objects)
ii  linux-signatures-nvidia-6.2.0-36-generic   6.2.0-36.37~22.04.1+1                   amd64        Linux kernel signatures for nvidia modules for version 6.2.0-36-generic
ii  linux-signatures-nvidia-6.2.0-37-generic   6.2.0-37.38~22.04.1                     amd64        Linux kernel signatures for nvidia modules for version 6.2.0-37-generic
ii  nvidia-compute-utils-535                   535.129.03-0ubuntu0.22.04.1             amd64        NVIDIA compute utilities
rc  nvidia-cuda-toolkit                        11.5.1-1ubuntu1                         amd64        NVIDIA CUDA development toolkit
ii  nvidia-dkms-535                            535.129.03-0ubuntu1                     amd64        NVIDIA DKMS package
ii  nvidia-driver-535                          535.129.03-0ubuntu0.22.04.1             amd64        NVIDIA driver metapackage
ii  nvidia-fs                                  2.18.3-1                                amd64        NVIDIA filesystem for GPUDirect Storage
ii  nvidia-fs-dkms                             2.18.3-1                                amd64        NVIDIA filesystem DKMS package
ii  nvidia-gds                                 12.3.1-1                                amd64        GPU Direct Storage meta-package
ii  nvidia-gds-12-3                            12.3.1-1                                amd64        GPU Direct Storage 12.3 meta-package
ii  nvidia-kernel-common-535                   535.129.03-0ubuntu1                     amd64        Shared files used with the kernel module
ii  nvidia-kernel-source-535                   535.129.03-0ubuntu0.22.04.1             amd64        NVIDIA kernel source package
ii  nvidia-prime                               0.8.17.1                                all          Tools to enable NVIDIA's Prime
ii  nvidia-settings                            545.23.08-0ubuntu1                      amd64        Tool for configuring the NVIDIA graphics driver
ii  nvidia-utils-535                           535.129.03-0ubuntu0.22.04.1             amd64        NVIDIA driver support binaries
ii  screen-resolution-extra                    0.18.2                                  all          Extension for the nvidia-settings control panel
ii  xserver-xorg-video-nvidia-535              535.129.03-0ubuntu0.22.04.1             amd64        NVIDIA binary Xorg driver

I did recently upgrade my Nvidia toolchain, but as far as I can tell I don't have any of the old versions left around. It looks like it chose the correct version of nvcc:

/home/rhettg/Projects/ollama/llm/llama.cpp/gguf/build/cuda/CMakeFiles/3.22.1/CMakeCUDACompiler.cmake 
$ cat CMakeCUDACompiler.cmake
set(CMAKE_CUDA_COMPILER "/usr/local/cuda/bin/nvcc")
set(CMAKE_CUDA_HOST_COMPILER "")
set(CMAKE_CUDA_HOST_LINK_LAUNCHER "/usr/bin/g++")
set(CMAKE_CUDA_COMPILER_ID "NVIDIA")
set(CMAKE_CUDA_COMPILER_VERSION "12.3.103")
set(CMAKE_CUDA_DEVICE_LINKER "/usr/local/cuda/bin/nvlink")
set(CMAKE_CUDA_FATBINARY "/usr/local/cuda/bin/fatbinary")
set(CMAKE_CUDA_STANDARD_COMPUTED_DEFAULT "17")
set(CMAKE_CUDA_EXTENSIONS_COMPUTED_DEFAULT "ON")
set(CMAKE_CUDA_COMPILE_FEATURES "cuda_std_03;cuda_std_11;cuda_std_14;cuda_std_17")
set(CMAKE_CUDA03_COMPILE_FEATURES "cuda_std_03")
set(CMAKE_CUDA11_COMPILE_FEATURES "cuda_std_11")
set(CMAKE_CUDA14_COMPILE_FEATURES "cuda_std_14")
set(CMAKE_CUDA17_COMPILE_FEATURES "cuda_std_17")
set(CMAKE_CUDA20_COMPILE_FEATURES "")
set(CMAKE_CUDA23_COMPILE_FEATURES "")

set(CMAKE_CUDA_PLATFORM_ID "Linux")
set(CMAKE_CUDA_SIMULATE_ID "GNU")
set(CMAKE_CUDA_COMPILER_FRONTEND_VARIANT "")
set(CMAKE_CUDA_SIMULATE_VERSION "11.4")



set(CMAKE_CUDA_COMPILER_ENV_VAR "CUDACXX")
set(CMAKE_CUDA_HOST_COMPILER_ENV_VAR "CUDAHOSTCXX")

set(CMAKE_CUDA_COMPILER_LOADED 1)
set(CMAKE_CUDA_COMPILER_ID_RUN 1)
set(CMAKE_CUDA_SOURCE_FILE_EXTENSIONS cu)
set(CMAKE_CUDA_LINKER_PREFERENCE 15)
set(CMAKE_CUDA_LINKER_PREFERENCE_PROPAGATES 1)

set(CMAKE_CUDA_SIZEOF_DATA_PTR "8")
set(CMAKE_CUDA_COMPILER_ABI "ELF")
set(CMAKE_CUDA_BYTE_ORDER "LITTLE_ENDIAN")
set(CMAKE_CUDA_LIBRARY_ARCHITECTURE "x86_64-linux-gnu")

if(CMAKE_CUDA_SIZEOF_DATA_PTR)
  set(CMAKE_SIZEOF_VOID_P "${CMAKE_CUDA_SIZEOF_DATA_PTR}")
endif()

if(CMAKE_CUDA_COMPILER_ABI)
  set(CMAKE_INTERNAL_PLATFORM_ABI "${CMAKE_CUDA_COMPILER_ABI}")
endif()

if(CMAKE_CUDA_LIBRARY_ARCHITECTURE)
  set(CMAKE_LIBRARY_ARCHITECTURE "x86_64-linux-gnu")
endif()

set(CMAKE_CUDA_COMPILER_TOOLKIT_ROOT "/usr/local/cuda")
set(CMAKE_CUDA_COMPILER_TOOLKIT_LIBRARY_ROOT "/usr/local/cuda")
set(CMAKE_CUDA_COMPILER_LIBRARY_ROOT "/usr/local/cuda")

set(CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES "/usr/local/cuda/targets/x86_64-linux/include")

set(CMAKE_CUDA_HOST_IMPLICIT_LINK_LIBRARIES "")
set(CMAKE_CUDA_HOST_IMPLICIT_LINK_DIRECTORIES "/usr/local/cuda/targets/x86_64-linux/lib/stubs;/usr/local/cuda/targets/x86_64-linux/lib")
set(CMAKE_CUDA_HOST_IMPLICIT_LINK_FRAMEWORK_DIRECTORIES "")

set(CMAKE_CUDA_IMPLICIT_INCLUDE_DIRECTORIES "/usr/include/c++/11;/usr/include/x86_64-linux-gnu/c++/11;/usr/include/c++/11/backward;/usr/lib/gcc/x86_64-linux-gnu/11/include;/usr/local/include;/usr/include/x86_64-linux-gnu;/usr/include")
set(CMAKE_CUDA_IMPLICIT_LINK_LIBRARIES "stdc++;m;gcc_s;gcc;c;gcc_s;gcc")
set(CMAKE_CUDA_IMPLICIT_LINK_DIRECTORIES "/usr/local/cuda/targets/x86_64-linux/lib/stubs;/usr/local/cuda/targets/x86_64-linux/lib;/usr/lib/gcc/x86_64-linux-gnu/11;/usr/lib/x86_64-linux-gnu;/usr/lib;/lib/x86_64-linux-gnu;/lib")
set(CMAKE_CUDA_IMPLICIT_LINK_FRAMEWORK_DIRECTORIES "")

set(CMAKE_CUDA_RUNTIME_LIBRARY_DEFAULT "STATIC")

set(CMAKE_LINKER "/usr/bin/ld")
set(CMAKE_AR "/usr/bin/ar")
set(CMAKE_MT "")

Any helping understand what's wrong here would be appreciated.

Originally created by @rhettg on GitHub (Dec 8, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1430 Originally assigned to: @dhiltgen on GitHub. This might be a llama.cpp question, but I'm struggling to get Ollama to work when I build it myself. The release builds work fine for me: ```console $ sudo -u ollama /usr/bin/ollama serve 2023/12/07 17:52:41 images.go:779: total blobs: 10 2023/12/07 17:52:41 images.go:786: total unused blobs removed: 0 2023/12/07 17:52:41 routes.go:777: Listening on 127.0.0.1:11434 (version 0.1.11) 2023/12/07 17:53:08 llama.go:291: 9973 MB VRAM available, loading up to 60 GPU layers 2023/12/07 17:53:08 llama.go:420: starting llama runner 2023/12/07 17:53:08 llama.go:478: waiting for llama runner to start responding ggml_init_cublas: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 3080, compute capability 8.6 {"timestamp":1702000389,"level":"INFO","function":"main","line":1323,"message":"build info","build":219,"commit":"9e70cc0"} {"timestamp":1702000389,"level":"INFO","function":"main","line":1325,"message":"system info","n_threads":8,"n_threads_batch":-1,"total_threads":16,"system_info":"AVX = 1 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | "} ``` But when I build it, I see this: ```console CUDA error 222 at /home/rhettg/Projects/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:7003: the provided PTX was compiled with an unsupported toolchain. current device: 0 2023/12/07 17:58:10 llama.go:441: 222 at /home/rhettg/Projects/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:7003: the provided PTX was compiled with an unsupported toolchain. current device: 0 2023/12/07 17:58:10 llama.go:449: error starting llama runner: llama runner process has terminated 2023/12/07 17:58:10 llama.go:515: llama runner stopped successfully ``` <details><summary>More version details:</summary> ```console $ git show HEAD commit dd427f499a65b2357f6b47ab3eed62478f42397a (HEAD -> main, origin/main, origin/HEAD) Merge: 2ae573c 02fe26c Author: Matt Williams <m@technovangelist.com> Date: Thu Dec 7 14:42:24 2023 -0800 Merge pull request #1419 from jmorganca/mattw/typescript-simplechat Simple chat example for typescript $ nvidia-smi Thu Dec 7 17:59:22 2023 +---------------------------------------------------------------------------------------+ | NVIDIA-SMI 535.129.03 Driver Version: 535.129.03 CUDA Version: 12.2 | |-----------------------------------------+----------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+======================+======================| | 0 NVIDIA GeForce RTX 3080 Off | 00000000:2B:00.0 On | N/A | | 0% 37C P8 23W / 320W | 2MiB / 10240MiB | 0% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+ +---------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=======================================================================================| | No running processes found | +---------------------------------------------------------------------------------------+ $ /usr/local/cuda/bin/nvcc --version nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2023 NVIDIA Corporation Built on Fri_Nov__3_17:16:49_PDT_2023 Cuda compilation tools, release 12.3, V12.3.103 Build cuda_12.3.r12.3/compiler.33492891_0 $ lsb_release -a No LSB modules are available. Distributor ID: Ubuntu Description: Ubuntu 22.04.3 LTS Release: 22.04 Codename: jammy $ dpkg -l | grep nvidia ii libnvidia-cfg1-535:amd64 535.129.03-0ubuntu0.22.04.1 amd64 NVIDIA binary OpenGL/GLX configuration library ii libnvidia-common-535 535.129.03-0ubuntu1 all Shared files used by the NVIDIA libraries ii libnvidia-compute-535:amd64 535.129.03-0ubuntu0.22.04.1 amd64 NVIDIA libcompute package ii libnvidia-compute-535:i386 535.129.03-0ubuntu0.22.04.1 i386 NVIDIA libcompute package ii libnvidia-decode-535:amd64 535.129.03-0ubuntu0.22.04.1 amd64 NVIDIA Video Decoding runtime libraries ii libnvidia-decode-535:i386 535.129.03-0ubuntu0.22.04.1 i386 NVIDIA Video Decoding runtime libraries ii libnvidia-encode-535:amd64 535.129.03-0ubuntu0.22.04.1 amd64 NVENC Video Encoding runtime library ii libnvidia-encode-535:i386 535.129.03-0ubuntu0.22.04.1 i386 NVENC Video Encoding runtime library ii libnvidia-extra-535:amd64 535.129.03-0ubuntu0.22.04.1 amd64 Extra libraries for the NVIDIA driver ii libnvidia-fbc1-535:amd64 535.129.03-0ubuntu0.22.04.1 amd64 NVIDIA OpenGL-based Framebuffer Capture runtime library ii libnvidia-fbc1-535:i386 535.129.03-0ubuntu0.22.04.1 i386 NVIDIA OpenGL-based Framebuffer Capture runtime library ii libnvidia-gl-535:amd64 535.129.03-0ubuntu0.22.04.1 amd64 NVIDIA OpenGL/GLX/EGL/GLES GLVND libraries and Vulkan ICD ii libnvidia-gl-535:i386 535.129.03-0ubuntu0.22.04.1 i386 NVIDIA OpenGL/GLX/EGL/GLES GLVND libraries and Vulkan ICD rc linux-modules-nvidia-535-6.2.0-26-generic 6.2.0-26.26~22.04.1+2 amd64 Linux kernel nvidia modules for version 6.2.0-26 ii linux-modules-nvidia-535-6.2.0-36-generic 6.2.0-36.37~22.04.1+1 amd64 Linux kernel nvidia modules for version 6.2.0-36 ii linux-modules-nvidia-535-6.2.0-37-generic 6.2.0-37.38~22.04.1 amd64 Linux kernel nvidia modules for version 6.2.0-37 ii linux-modules-nvidia-535-generic-hwe-22.04 6.2.0-37.38~22.04.1 amd64 Extra drivers for nvidia-535 for the generic-hwe-22.04 flavour rc linux-objects-nvidia-535-6.2.0-26-generic 6.2.0-26.26~22.04.1+2 amd64 Linux kernel nvidia modules for version 6.2.0-26 (objects) ii linux-objects-nvidia-535-6.2.0-36-generic 6.2.0-36.37~22.04.1+1 amd64 Linux kernel nvidia modules for version 6.2.0-36 (objects) ii linux-objects-nvidia-535-6.2.0-37-generic 6.2.0-37.38~22.04.1 amd64 Linux kernel nvidia modules for version 6.2.0-37 (objects) ii linux-signatures-nvidia-6.2.0-36-generic 6.2.0-36.37~22.04.1+1 amd64 Linux kernel signatures for nvidia modules for version 6.2.0-36-generic ii linux-signatures-nvidia-6.2.0-37-generic 6.2.0-37.38~22.04.1 amd64 Linux kernel signatures for nvidia modules for version 6.2.0-37-generic ii nvidia-compute-utils-535 535.129.03-0ubuntu0.22.04.1 amd64 NVIDIA compute utilities rc nvidia-cuda-toolkit 11.5.1-1ubuntu1 amd64 NVIDIA CUDA development toolkit ii nvidia-dkms-535 535.129.03-0ubuntu1 amd64 NVIDIA DKMS package ii nvidia-driver-535 535.129.03-0ubuntu0.22.04.1 amd64 NVIDIA driver metapackage ii nvidia-fs 2.18.3-1 amd64 NVIDIA filesystem for GPUDirect Storage ii nvidia-fs-dkms 2.18.3-1 amd64 NVIDIA filesystem DKMS package ii nvidia-gds 12.3.1-1 amd64 GPU Direct Storage meta-package ii nvidia-gds-12-3 12.3.1-1 amd64 GPU Direct Storage 12.3 meta-package ii nvidia-kernel-common-535 535.129.03-0ubuntu1 amd64 Shared files used with the kernel module ii nvidia-kernel-source-535 535.129.03-0ubuntu0.22.04.1 amd64 NVIDIA kernel source package ii nvidia-prime 0.8.17.1 all Tools to enable NVIDIA's Prime ii nvidia-settings 545.23.08-0ubuntu1 amd64 Tool for configuring the NVIDIA graphics driver ii nvidia-utils-535 535.129.03-0ubuntu0.22.04.1 amd64 NVIDIA driver support binaries ii screen-resolution-extra 0.18.2 all Extension for the nvidia-settings control panel ii xserver-xorg-video-nvidia-535 535.129.03-0ubuntu0.22.04.1 amd64 NVIDIA binary Xorg driver ``` </details> I did recently upgrade my Nvidia toolchain, but as far as I can tell I don't have any of the old versions left around. It looks like it chose the correct version of `nvcc`: <details><summary>/home/rhettg/Projects/ollama/llm/llama.cpp/gguf/build/cuda/CMakeFiles/3.22.1/CMakeCUDACompiler.cmake</summary> ```make $ cat CMakeCUDACompiler.cmake set(CMAKE_CUDA_COMPILER "/usr/local/cuda/bin/nvcc") set(CMAKE_CUDA_HOST_COMPILER "") set(CMAKE_CUDA_HOST_LINK_LAUNCHER "/usr/bin/g++") set(CMAKE_CUDA_COMPILER_ID "NVIDIA") set(CMAKE_CUDA_COMPILER_VERSION "12.3.103") set(CMAKE_CUDA_DEVICE_LINKER "/usr/local/cuda/bin/nvlink") set(CMAKE_CUDA_FATBINARY "/usr/local/cuda/bin/fatbinary") set(CMAKE_CUDA_STANDARD_COMPUTED_DEFAULT "17") set(CMAKE_CUDA_EXTENSIONS_COMPUTED_DEFAULT "ON") set(CMAKE_CUDA_COMPILE_FEATURES "cuda_std_03;cuda_std_11;cuda_std_14;cuda_std_17") set(CMAKE_CUDA03_COMPILE_FEATURES "cuda_std_03") set(CMAKE_CUDA11_COMPILE_FEATURES "cuda_std_11") set(CMAKE_CUDA14_COMPILE_FEATURES "cuda_std_14") set(CMAKE_CUDA17_COMPILE_FEATURES "cuda_std_17") set(CMAKE_CUDA20_COMPILE_FEATURES "") set(CMAKE_CUDA23_COMPILE_FEATURES "") set(CMAKE_CUDA_PLATFORM_ID "Linux") set(CMAKE_CUDA_SIMULATE_ID "GNU") set(CMAKE_CUDA_COMPILER_FRONTEND_VARIANT "") set(CMAKE_CUDA_SIMULATE_VERSION "11.4") set(CMAKE_CUDA_COMPILER_ENV_VAR "CUDACXX") set(CMAKE_CUDA_HOST_COMPILER_ENV_VAR "CUDAHOSTCXX") set(CMAKE_CUDA_COMPILER_LOADED 1) set(CMAKE_CUDA_COMPILER_ID_RUN 1) set(CMAKE_CUDA_SOURCE_FILE_EXTENSIONS cu) set(CMAKE_CUDA_LINKER_PREFERENCE 15) set(CMAKE_CUDA_LINKER_PREFERENCE_PROPAGATES 1) set(CMAKE_CUDA_SIZEOF_DATA_PTR "8") set(CMAKE_CUDA_COMPILER_ABI "ELF") set(CMAKE_CUDA_BYTE_ORDER "LITTLE_ENDIAN") set(CMAKE_CUDA_LIBRARY_ARCHITECTURE "x86_64-linux-gnu") if(CMAKE_CUDA_SIZEOF_DATA_PTR) set(CMAKE_SIZEOF_VOID_P "${CMAKE_CUDA_SIZEOF_DATA_PTR}") endif() if(CMAKE_CUDA_COMPILER_ABI) set(CMAKE_INTERNAL_PLATFORM_ABI "${CMAKE_CUDA_COMPILER_ABI}") endif() if(CMAKE_CUDA_LIBRARY_ARCHITECTURE) set(CMAKE_LIBRARY_ARCHITECTURE "x86_64-linux-gnu") endif() set(CMAKE_CUDA_COMPILER_TOOLKIT_ROOT "/usr/local/cuda") set(CMAKE_CUDA_COMPILER_TOOLKIT_LIBRARY_ROOT "/usr/local/cuda") set(CMAKE_CUDA_COMPILER_LIBRARY_ROOT "/usr/local/cuda") set(CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES "/usr/local/cuda/targets/x86_64-linux/include") set(CMAKE_CUDA_HOST_IMPLICIT_LINK_LIBRARIES "") set(CMAKE_CUDA_HOST_IMPLICIT_LINK_DIRECTORIES "/usr/local/cuda/targets/x86_64-linux/lib/stubs;/usr/local/cuda/targets/x86_64-linux/lib") set(CMAKE_CUDA_HOST_IMPLICIT_LINK_FRAMEWORK_DIRECTORIES "") set(CMAKE_CUDA_IMPLICIT_INCLUDE_DIRECTORIES "/usr/include/c++/11;/usr/include/x86_64-linux-gnu/c++/11;/usr/include/c++/11/backward;/usr/lib/gcc/x86_64-linux-gnu/11/include;/usr/local/include;/usr/include/x86_64-linux-gnu;/usr/include") set(CMAKE_CUDA_IMPLICIT_LINK_LIBRARIES "stdc++;m;gcc_s;gcc;c;gcc_s;gcc") set(CMAKE_CUDA_IMPLICIT_LINK_DIRECTORIES "/usr/local/cuda/targets/x86_64-linux/lib/stubs;/usr/local/cuda/targets/x86_64-linux/lib;/usr/lib/gcc/x86_64-linux-gnu/11;/usr/lib/x86_64-linux-gnu;/usr/lib;/lib/x86_64-linux-gnu;/lib") set(CMAKE_CUDA_IMPLICIT_LINK_FRAMEWORK_DIRECTORIES "") set(CMAKE_CUDA_RUNTIME_LIBRARY_DEFAULT "STATIC") set(CMAKE_LINKER "/usr/bin/ld") set(CMAKE_AR "/usr/bin/ar") set(CMAKE_MT "") ``` </details> Any helping understand what's wrong here would be appreciated.
GiteaMirror added the nvidia label 2026-05-03 10:21:39 -05:00
GiteaMirror commented 2026-05-03 10:21:47 -05:00
Author
Owner
Copy Link

@Gh0stExp10it commented on GitHub (Dec 15, 2023):

I've fixed some of the same issues, especially the "The CUDA compiler identification is unknown", by adding the nvcc directory to the PATH env (my system here is a WSL2-Ubuntu):

export PATH=$PATH:/usr/local/cuda/bin
source ~/.bashrc

Hope this helps!

<!-- gh-comment-id:1858063546 --> @Gh0stExp10it commented on GitHub (Dec 15, 2023): I've fixed some of the same issues, especially the "The CUDA compiler identification is unknown", by adding the ```nvcc``` directory to the PATH env (my system here is a WSL2-Ubuntu): ```sh export PATH=$PATH:/usr/local/cuda/bin source ~/.bashrc ``` Hope this helps!
GiteaMirror commented 2026-05-03 10:21:48 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jan 27, 2024):

@rhettg please give it a try on the latest commit on main. We've been steadily improving the generate scripts to try to auto-discover tools and paths, while providing the ability to explicitly specify their location. Please also consult https://github.com/ollama/ollama/blob/main/docs/development.md for instructions and dependencies.

<!-- gh-comment-id:1912909404 --> @dhiltgen commented on GitHub (Jan 27, 2024): @rhettg please give it a try on the latest commit on main. We've been steadily improving the generate scripts to try to auto-discover tools and paths, while providing the ability to explicitly specify their location. Please also consult https://github.com/ollama/ollama/blob/main/docs/development.md for instructions and dependencies.
GiteaMirror commented 2026-05-03 10:21:50 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Feb 1, 2024):

If you're still having problems with 0.1.22 or newer, please re-open.

<!-- gh-comment-id:1922458145 --> @dhiltgen commented on GitHub (Feb 1, 2024): If you're still having problems with 0.1.22 or newer, please re-open.
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 nvidia
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#62798
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?