github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3261] 404 while installing NVIDIA repository #27766

New Issue
Closed
opened 2026-04-22 05:20:38 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 05:20:38 -05:00
Owner
Copy Link

Originally created by @gnumoksha on GitHub (Mar 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3261

What is the issue?

$ curl -fsSL https://ollama.com/install.sh | sh
>>> Downloading ollama...
######################################################################## 100.0%#=#=#                                    ######################################################################## 100.0%
>>> Installing ollama to /usr/local/bin...
>>> Adding ollama user to render group...
>>> Adding ollama user to video group...
>>> Adding current user to ollama group...
>>> Creating ollama systemd service...
>>> Enabling and starting ollama service...
>>> Installing NVIDIA repository...
curl: (22) The requested URL returned error: 404

What did you expect to see?

ollama installed and running

Steps to reproduce

  • Create a AWS instance of type g5g.xlarge
  • Try to install ollama

Are there any recent changes that introduced the issue?

No response

OS

Linux

Architecture

arm64

Platform

No response

Ollama version

No response

GPU

Nvidia

GPU info

$ lspci -d '10de:'
00:1f.0 3D controller: NVIDIA Corporation TU104GL [T4G] (rev a1)

CPU

Other

Other software

$ lscpu
Architecture:           aarch64
  CPU op-mode(s):       32-bit, 64-bit
  Byte Order:           Little Endian
CPU(s):                 4
  On-line CPU(s) list:  0-3
Vendor ID:              ARM
  Model name:           Neoverse-N1
    Model:              1
    Thread(s) per core: 1
    Core(s) per socket: 4
    Socket(s):          1
    Stepping:           r3p1
    BogoMIPS:           243.75
    Flags:              fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm lrcpc dcpop asimd
                        dp ssbs
[...]
Originally created by @gnumoksha on GitHub (Mar 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3261 ### What is the issue? ```console $ curl -fsSL https://ollama.com/install.sh | sh >>> Downloading ollama... ######################################################################## 100.0%#=#=# ######################################################################## 100.0% >>> Installing ollama to /usr/local/bin... >>> Adding ollama user to render group... >>> Adding ollama user to video group... >>> Adding current user to ollama group... >>> Creating ollama systemd service... >>> Enabling and starting ollama service... >>> Installing NVIDIA repository... curl: (22) The requested URL returned error: 404 ``` ### What did you expect to see? ollama installed and running ### Steps to reproduce - Create a AWS instance of type `g5g.xlarge` - Try to install ollama ### Are there any recent changes that introduced the issue? _No response_ ### OS Linux ### Architecture arm64 ### Platform _No response_ ### Ollama version _No response_ ### GPU Nvidia ### GPU info ```console $ lspci -d '10de:' 00:1f.0 3D controller: NVIDIA Corporation TU104GL [T4G] (rev a1) ``` ### CPU Other ### Other software ```console $ lscpu Architecture: aarch64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 4 On-line CPU(s) list: 0-3 Vendor ID: ARM Model name: Neoverse-N1 Model: 1 Thread(s) per core: 1 Core(s) per socket: 4 Socket(s): 1 Stepping: r3p1 BogoMIPS: 243.75 Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm lrcpc dcpop asimd dp ssbs [...] ```
GiteaMirror added the nvidiabug labels 2026-04-22 05:20:38 -05:00
GiteaMirror commented 2026-04-22 05:20:40 -05:00
Author
Owner
Copy Link

@gnumoksha commented on GitHub (Mar 20, 2024):

There are two issues:

  1. Here 7ed3e94105/scripts/install.sh (L225) uname -m returns aarch64 but according to nvidia docs there is only arm64.
  2. There is no arm64 for ubuntu 22.04 according to nvidia docs.

nvidia docs

<!-- gh-comment-id:2008484357 --> @gnumoksha commented on GitHub (Mar 20, 2024): There are two issues: 1) Here https://github.com/ollama/ollama/blob/7ed3e941058a47464a1ee97cd16f464eb788e396/scripts/install.sh#L225 `uname -m` returns `aarch64` but according to nvidia docs there is only `arm64`. 2) There is no arm64 for ubuntu 22.04 according to nvidia docs. [nvidia docs](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#network-repo-installation-for-ubuntu)
GiteaMirror commented 2026-04-22 05:20:41 -05:00
Author
Owner
Copy Link

@gnumoksha commented on GitHub (Mar 20, 2024):

Using Ubuntu 20.04 and manually fixing issue 1, produces the error "E: Unable to locate package cuda-drivers".

<!-- gh-comment-id:2008535473 --> @gnumoksha commented on GitHub (Mar 20, 2024): Using Ubuntu 20.04 and manually fixing issue 1, produces the error "E: Unable to locate package cuda-drivers".
GiteaMirror commented 2026-04-22 05:20:41 -05:00
Author
Owner
Copy Link

@roberto-formulatrix commented on GitHub (Jun 29, 2024):

Has this problem been resolved? I get the same:

Get:20 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/x86_64  Packages [22.9 kB]
Fetched 27.1 kB in 3s (9,182 B/s)
Reading package lists... Done
Reading package lists...
Building dependency tree...
Reading state information...
E: Unable to locate package cuda-drivers

user@beausoleil:~$ lspci
00:02.0 PCI bridge: NVIDIA Corporation Device 0faf (rev a1)
01:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller (rev 15)
<!-- gh-comment-id:2198266963 --> @roberto-formulatrix commented on GitHub (Jun 29, 2024): Has this problem been resolved? I get the same: ``` Get:20 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/x86_64 Packages [22.9 kB] Fetched 27.1 kB in 3s (9,182 B/s) Reading package lists... Done Reading package lists... Building dependency tree... Reading state information... E: Unable to locate package cuda-drivers user@beausoleil:~$ lspci 00:02.0 PCI bridge: NVIDIA Corporation Device 0faf (rev a1) 01:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller (rev 15) ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug 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#27766
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?