fac9060da5
Init submodule with new path
2024-01-04 13:00:13 -08:00
a554616f8e
remove old llama.cpp submodule path
2024-01-04 12:12:21 -08:00
77d96da94b
Code shuffle to clean up the llm dir
2024-01-04 12:12:05 -08:00
0d6e3565ae
Add embeddings to API ( #1773 )
2024-01-04 15:00:52 -05:00
b5939008a1
Merge pull request #1785 from dhiltgen/win_native_cli
...
Load dynamic cpu lib on windows
2024-01-04 08:55:01 -08:00
e9ce91e9a6
Load dynamic cpu lib on windows
...
On linux, we link the CPU library in to the Go app and fall back to it
when no GPU match is found. On windows we do not link in the CPU library
so that we can better control our dependencies for the CLI. This fixes
the logic so we correctly fallback to the dynamic CPU library
on windows.
2024-01-04 08:41:41 -08:00
4ad6c9b11f
fix: pull either original model or from model on create ( #1774 )
2024-01-04 01:34:38 -05:00
c0285158a9
tweak memory requirements error text
2024-01-03 19:47:18 -05:00
77a66df72c
add macOS memory check for 47B models
2024-01-03 19:46:16 -05:00
5b4837f881
remove unused filetype check
2024-01-03 19:45:39 -05:00
29340c2e62
update cmake flags for amd64 macOS ( #1780 )
...
* update cmake flags for intel macOS
* remove `LLAMA_K_QUANTS`
* put back `CMAKE_OSX_DEPLOYMENT_TARGET` and disable `LLAMA_F16C`
2024-01-03 19:22:15 -05:00
d5ec730354
Merge pull request #1779 from dhiltgen/refined_amd_gpu_list
...
Improve maintainability of Radeon card list
2024-01-03 16:18:57 -08:00
8bed487aba
Merge pull request #1778 from dhiltgen/wsl1
...
Fail fast on WSL1 while allowing on WSL2
2024-01-03 16:18:41 -08:00
c1a10a6e9b
Merge pull request #1781 from dhiltgen/cpu_only_build
...
Fix CPU only builds
2024-01-03 16:18:25 -08:00
ddbfa6fe31
Fix CPU only builds
...
Go embed doesn't like when there's no matching files, so put
a dummy placeholder in to allow building without any GPU support
If no "server" library is found, it's safely ignored at runtime.
2024-01-03 16:08:34 -08:00
2fcd41ef81
Fail fast on WSL1 while allowing on WSL2
...
This prevents users from accidentally installing on WSL1 with instructions
guiding how to upgrade their WSL instance to version 2. Once running WSL2
if you have an NVIDIA card, you can follow their instructions to set up
GPU passthrough and run models on the GPU. This is not possible on WSL1.
2024-01-03 16:02:32 -08:00
16f4603b67
Improve maintainability of Radeon card list
...
This moves the list of AMD GPUs to an easier to maintain list which
should make it easier to update over time.
2024-01-03 15:16:56 -08:00
1184686649
Merge pull request #1776 from dhiltgen/render_group
...
Add ollama user to render group for Radeon support
2024-01-03 13:07:54 -08:00
2588cb2daa
Add ollama user to render group for Radeon support
...
For the ROCm libraries to access the driver, we need to add the ollama user
to the render group.
2024-01-03 12:56:31 -08:00
c7ea8f237e
set num_gpu to 1 only by default on darwin arm64 ( #1771 )
2024-01-03 14:10:29 -05:00
0b3118e0af
fix: relay request opts to loaded llm prediction ( #1761 )
2024-01-03 12:01:42 -05:00
05face44ef
Merge pull request #1683 from dhiltgen/fix_windows_test
...
Fix windows system memory lookup
2024-01-03 09:00:39 -08:00
a2ad952440
Fix windows system memory lookup
...
This refines the gpu package error handling and fixes a bug with the
system memory lookup on windows.
2024-01-03 08:50:01 -08:00
5fea4410be
Merge pull request #1680 from dhiltgen/better_patching
...
Refactor how we augment llama.cpp and refine windows native build
2024-01-03 08:10:17 -08:00
b846eb64d0
Fix template api doc description ( #1661 )
2024-01-03 11:00:59 -05:00
3c5dd9ed1d
Update README.md ( #1766 )
2024-01-03 10:44:22 -05:00
b17ccd0542
Update import.md
2024-01-02 22:28:18 -05:00
d0409f772f
keyboard shortcut help ( #1764 )
2024-01-02 18:04:12 -08:00
ec261422af
use docker build in build scripts
2024-01-02 19:32:54 -05:00
0498f7ce56
Get rid of one-line llama.log
...
This one log line was triggering a single line llama.log to be generated
in the pwd of the server
2024-01-02 15:36:16 -08:00
738a8d12eb
Rename the ollama cmakefile
2024-01-02 15:36:16 -08:00
d966b730ac
Switch windows build to fully dynamic
...
Refactor where we store build outputs, and support a fully dynamic loading
model on windows so the base executable has no special dependencies thus
doesn't require a special PATH.
2024-01-02 15:36:16 -08:00
9a70aecccb
Refactor how we augment llama.cpp
...
This changes the model for llama.cpp inclusion so we're not applying a patch,
but instead have the C++ code directly in the ollama tree, which should make it
easier to refine and update over time.
2024-01-02 15:35:55 -08:00
22cd5eaab6
Added Ollama-SwiftUI to integrations ( #1747 )
2024-01-02 09:47:50 -05:00
304a8799ca
Update README.md ( #1757 )
2024-01-02 09:47:08 -05:00
2a2fa3c329
api.md cleanup & formatting
2023-12-27 14:32:35 -05:00
55978c1dc9
clean up cache api option
2023-12-27 14:27:45 -05:00
d4ebdadbe7
enable cache_prompt by default
2023-12-27 14:23:42 -05:00
e201efa14b
Add windows native build instructions
2023-12-25 08:31:34 -08:00
c5f21f73a4
follow best practices by adding resp.Body.Close() ( #1708 )
2023-12-25 09:01:37 -05:00
371bc73531
Update README.md
2023-12-24 11:54:08 -05:00
c651d8b824
Update README.md
2023-12-23 11:18:12 -05:00
cf50ef5b51
Merge pull request #1684 from dhiltgen/tag_integration_tests
...
Guard integration tests with a tag
2023-12-22 16:43:41 -08:00
697bea6939
Guard integration tests with a tag
...
This should help CI avoid running the integration test logic in a
container where it's not currently possible.
2023-12-22 16:33:27 -08:00
10da41d677
Add Cache flag to api ( #1642 )
2023-12-22 17:16:20 -05:00
db356c8519
post-response templating ( #1427 )
2023-12-22 17:07:05 -05:00
b80081022f
cache docker builds in build_linux.sh
2023-12-22 16:01:20 -05:00
790457398a
Merge pull request #1677 from jmorganca/mattw/docrunupdate
...
update where are models stored q
2023-12-22 09:56:27 -08:00
511069a2a5
update where are models stored q
...
Signed-off-by: Matt Williams <m@technovangelist.com >
2023-12-22 09:48:44 -08:00
5a85070c22
Update readmes, requirements, packagejsons, etc for all examples ( #1452 )
...
Most of the examples needed updates of Readmes to show how to run them. Some of the requirements.txt files had extra content that wasn't needed, or missing altogether. Apparently some folks like to run npm start
to run typescript, so a script was added to all typescript examples which
hadn't been done before.
Basically just a lot of cleanup.
Signed-off-by: Matt Williams <m@technovangelist.com >
2023-12-22 09:10:41 -08:00
