jmorganca
ac6b154cc4
update to d5c938cd
2024-07-29 15:38:51 -07:00
jmorganca
878eb9a19f
add llava
2024-07-29 15:38:51 -07:00
jmorganca
5818e3b210
llama: add clip dependencies
2024-07-29 15:38:51 -07:00
jmorganca
57d03929cd
fix build on windows
2024-07-29 15:38:51 -07:00
jmorganca
0a6b1adbd7
fix ggml-metal.m build constraints
2024-07-29 15:38:51 -07:00
jmorganca
ec60d79a67
fix ggml-metal.m
2024-07-29 15:38:51 -07:00
jmorganca
460d9857e2
fix sync script
2024-07-29 15:38:51 -07:00
jmorganca
4dd63c1fef
move runner package down
2024-07-29 15:38:51 -07:00
Daniel Hiltgen
ce3c93b08f
Report better error on cuda unsupported os/arch
...
If we detect an NVIDIA GPU, but nvidia doesn't support the os/arch,
this will report a better error for the user and point them to docs
to self-install the drivers if possible.
2024-07-24 17:09:20 -07:00
Daniel Hiltgen
b44320db13
Bundle missing CRT libraries
...
Some users are experienging runner startup errors due
to not having these msvc redist libraries on their host
2024-07-08 18:24:21 -07:00
Daniel Hiltgen
4f67b39d26
Centos 7 EOL broke mirrors
...
As of July 1st 2024: Could not resolve host: mirrorlist.centos.org
This is expected due to EOL dates.
2024-07-02 09:22:17 -07:00
Daniel Hiltgen
54a79d6a8a
Merge pull request #5125 from dhiltgen/fedora39
...
Bump latest fedora cuda repo to 39
2024-06-20 11:27:24 -07:00
Daniel Hiltgen
1a1c99e334
Bump latest fedora cuda repo to 39
2024-06-18 17:13:54 -07:00
Daniel Hiltgen
b2799f111b
Move libraries out of users path
...
We update the PATH on windows to get the CLI mapped, but this has
an unintended side effect of causing other apps that may use our bundled
DLLs to get terminated when we upgrade.
2024-06-17 13:12:18 -07:00
jayson-cloude
157f09acdf
fix: "Skip searching for network devices"
...
On an Ubuntu 24.04 computer with vmware installed, the sudo lshw command will get stuck. "Network interfaces" is always displayed
2024-06-11 16:11:35 +08:00
Jeffrey Morgan
1f5008544b
Update install.sh
2024-05-28 15:01:22 -07:00
Jeffrey Morgan
45cbfc5aee
fix wsl2 status check for nvidia cards ( #4689 )
2024-05-28 14:49:46 -07:00
Jeffrey Morgan
6d423b383b
Improve install experience on WSL2 and Linux ( #4653 )
2024-05-28 14:41:50 -07:00
Jeffrey Morgan
b7d316d98d
fix nvidia detection in install script ( #4683 )
2024-05-28 09:59:36 -07:00
Jeffrey Morgan
c79f8c9c39
Ensure nvidia and nvidia_uvm kernel modules are loaded in install.sh script and at startup ( #4652 )
...
* ensure kernel modules are loaded in `install.sh` script and at startup
* indentation
* use `SUDO` variable
* restart if nouveau is detected
* consistent success message for AMD
2024-05-26 14:57:17 -07:00
Jeffrey Morgan
485016bfbb
Update install.sh
2024-05-26 11:46:00 -07:00
Daniel Hiltgen
e592e8fccb
Support Fedoras standard ROCm location
2024-05-01 15:47:12 -07:00
Hernan Martinez
6d3152a98a
Use architecture specific folders in installer script
2024-04-26 23:35:16 -06:00
Hernan Martinez
204349b17b
Use architecture specific folders in the build script
2024-04-26 23:26:03 -06:00
Daniel Hiltgen
40bc4622ef
Fix exe name for zip packaging on windows
...
The zip file encodes the OS and architecture, so keep the short exe name
2024-04-26 09:18:05 -07:00
Daniel Hiltgen
8feb97dc0d
Move cuda/rocm dependency gathering into generate script
...
This will make it simpler for CI to accumulate artifacts from prior steps
2024-04-25 22:38:44 -07:00
Daniel Hiltgen
058f6cd2cc
Move nested payloads to installer and zip file on windows
...
Now that the llm runner is an executable and not just a dll, more users are facing
problems with security policy configurations on windows that prevent users
writing to directories and then executing binaries from the same location.
This change removes payloads from the main executable on windows and shifts them
over to be packaged in the installer and discovered based on the executables location.
This also adds a new zip file for people who want to "roll their own" installation model.
2024-04-23 16:14:47 -07:00
Daniel Hiltgen
539043f5e0
CI automation for tagging latest images
2024-03-28 16:07:37 -07:00
Patrick Devine
1b272d5bcd
change github.com/jmorganca/ollama to github.com/ollama/ollama ( #3347 )
2024-03-26 13:04:17 -07:00
Daniel Hiltgen
b8c2be6142
Use Rocky Linux Vault to get GCC 10.2 installed
...
This should hopefully only be a temporary workaround until Rocky 8
picks up GCC 10.4 which fixes the NVCC bug
2024-03-25 19:18:50 -07:00
Daniel Hiltgen
949b6c01e0
Revamp go based integration tests
...
This uplevels the integration tests to run the server which can allow
testing an existing server, or a remote server.
2024-03-23 14:24:18 +01:00
Daniel Hiltgen
540f4af45f
Wire up more complete CI for releases
...
Flesh out our github actions CI so we can build official releaes.
2024-03-15 12:37:36 -07:00
Daniel Hiltgen
6459377ae0
Add ROCm support to linux install script ( #2966 )
2024-03-14 18:00:16 -07:00
Jeffrey Morgan
b5fcd9d3aa
use -trimpath when building releases ( #3069 )
2024-03-11 15:58:46 -07:00
Jeffrey Morgan
cdf65e793f
only copy deps for amd64 in build_linux.sh
2024-03-09 17:55:22 -08:00
Daniel Hiltgen
6c5ccb11f9
Revamp ROCm support
...
This refines where we extract the LLM libraries to by adding a new
OLLAMA_HOME env var, that defaults to `~/.ollama` The logic was already
idempotenent, so this should speed up startups after the first time a
new release is deployed. It also cleans up after itself.
We now build only a single ROCm version (latest major) on both windows
and linux. Given the large size of ROCms tensor files, we split the
dependency out. It's bundled into the installer on windows, and a
separate download on windows. The linux install script is now smart and
detects the presence of AMD GPUs and looks to see if rocm v6 is already
present, and if not, then downloads our dependency tar file.
For Linux discovery, we now use sysfs and check each GPU against what
ROCm supports so we can degrade to CPU gracefully instead of having
llama.cpp+rocm assert/crash on us. For Windows, we now use go's windows
dynamic library loading logic to access the amdhip64.dll APIs to query
the GPU information.
2024-03-07 10:36:50 -08:00
Daniel Hiltgen
74468513bd
Add ollama user to video group
...
On OpenSUSE, ollama needs to be a member of the video group
to access the GPU
2024-02-29 08:50:10 -08:00
Daniel Hiltgen
98e0b7e94f
Refine container image build script
...
Allow overriding the platform, image name, and tag latest for
standard and rocm images.
2024-02-26 17:26:49 -08:00
Jeffrey Morgan
275ea01587
restore windows build flags and compression
2024-02-22 18:07:18 -05:00
Jeffrey Morgan
8782dd5628
fix build_windows.ps1 script to run go build with the correct flags
2024-02-22 17:41:43 -05:00
Josh
f983ef7f5f
Update install.sh success message
2024-02-21 18:30:01 -05:00
Jeffrey Morgan
1ae1c33651
Windows build + installer adjustments ( #2656 )
...
* remove `-w -s` linker flags on windows
* use `zip` for windows installer compression
2024-02-21 18:21:26 -05:00
Jeffrey Morgan
92423b0600
add dist directory in build_windows.ps
2024-02-21 00:05:05 -05:00
Daniel Hiltgen
df6dc4fd96
Fix duplicate menus on update and exit on signals
...
Also fixes a few fit-and-finish items for better developer experience
2024-02-16 15:33:16 -08:00
Daniel Hiltgen
272e53a1f5
Prepare to distribute standalone windows executable
...
This will be useful for our automated test riggig, and may be useful for
advanced users who want to "roll their own" system service
2024-02-15 14:56:55 -08:00
jmorganca
7ad9844ac0
set exe metadata using resource files
2024-02-15 05:56:45 +00:00
Daniel Hiltgen
29e90cc13b
Implement new Go based Desktop app
...
This focuses on Windows first, but coudl be used for Mac
and possibly linux in the future.
2024-02-15 05:56:45 +00:00
Daniel Hiltgen
9da9e8fb72
Move Mac App to a new dir
2024-02-15 05:56:45 +00:00
Jeffrey Morgan
1c8435ffa9
Update domain name references in docs and install script ( #2435 )
2024-02-09 15:19:30 -08:00
Daniel Hiltgen
75c44aa319
Add back ROCm container support
...
This adds ROCm support back as a discrete image.
2024-01-26 09:24:29 -08:00
