e02ecfb6c8
Merge pull request #2116 from dhiltgen/cc_50_80
...
Add support for CUDA 5.0 cards
2024-01-27 10:28:38 -08:00
df54c723ae
Make CPU builds parallel and customizable AMD GPUs
...
The linux build now support parallel CPU builds to speed things up.
This also exposes AMD GPU targets as an optional setting for advaced
users who want to alter our default set.
2024-01-21 15:12:21 -08:00
a447a083f2
Add compute capability 5.0, 7.5, and 8.0
2024-01-20 14:24:05 -08:00
abec7f06e5
Merge pull request #2056 from dhiltgen/slog
...
Mechanical switch from log to slog
2024-01-18 14:27:24 -08:00
ecbfc0182f
Go bump to v1.21 to pick up slog
2024-01-18 14:12:57 -08:00
fedd705aea
Mechanical switch from log to slog
...
A few obvious levels were adjusted, but generally everything mapped to "info" level.
2024-01-18 14:12:57 -08:00
9cd20b0ec8
Refine the linux cuda/rocm developer docs
2024-01-18 09:44:44 -08:00
d88c527be3
Build multiple CPU variants and pick the best
...
This reduces the built-in linux version to not use any vector extensions
which enables the resulting builds to run under Rosetta on MacOS in
Docker. Then at runtime it checks for the actual CPU vector
extensions and loads the best CPU library available
2024-01-11 08:42:47 -08:00
e201efa14b
Add windows native build instructions
2023-12-25 08:31:34 -08:00
e5202eb687
Quiet down llama.cpp logging by default
...
By default builds will now produce non-debug and non-verbose binaries.
To enable verbose logs in llama.cpp and debug symbols in the
native code, set `CGO_CFLAGS=-g`
2023-12-22 08:47:18 -08:00
1b991d0ba9
Refine build to support CPU only
...
If someone checks out the ollama repo and doesn't install the CUDA
library, this will ensure they can build a CPU only version
2023-12-19 09:05:46 -08:00
4fc10acce9
add some missing code directives in docs ( #664 )
2023-10-01 11:51:01 -07:00
6c6a31a1e8
embed libraries using cmake
2023-09-20 14:41:57 -07:00
fc6ec356fc
remove libcuda.so
2023-09-20 20:36:14 +01:00
1255bc9b45
only package 11.8 runner
2023-09-20 20:00:41 +01:00
4e8be787c7
pack in cuda libs
2023-09-20 17:40:42 +01:00
2540c9181c
support for packaging in multiple cuda runners ( #509 )
...
* enable packaging multiple cuda versions
* use nvcc cuda version if available
---------
Co-authored-by: Michael Yang <mxyng@pm.me >
2023-09-14 15:08:13 -04:00
f221637053
first pass at linux gpu support ( #454 )
...
* linux gpu support
* handle multiple gpus
* add cuda docker image (#488 )
---------
Co-authored-by: Michael Yang <mxyng@pm.me >
2023-09-12 11:04:35 -04:00
42998d797d
subprocess llama.cpp server ( #401 )
...
* remove c code
* pack llama.cpp
* use request context for llama_cpp
* let llama_cpp decide the number of threads to use
* stop llama runner when app stops
* remove sample count and duration metrics
* use go generate to get libraries
* tmp dir for running llm
2023-08-30 16:35:03 -04:00
041f9ad1a1
update README.md
2023-08-25 11:44:25 -07:00
1f78e409b4
docs: format with prettier
2023-08-08 15:41:48 -07:00
24e43e3212
update development.md
2023-07-24 09:43:57 -07:00
52f04e39f2
Note that CGO must be enabled in dev docs
2023-07-21 22:36:36 +02:00
3d9498dc95
Some simple modelfile examples
...
Signed-off-by: Matt Williams <m@technovangelist.com >
2023-07-17 17:16:59 -07:00
1358e27b77
add publish script
2023-07-07 12:59:45 -04:00
9811956938
update development.md
2023-06-28 12:41:30 -07:00
9ba58c8a9e
move desktop docs to desktop/
2023-06-28 11:29:29 -04:00
9f868d8258
move desktop docs to desktop/
2023-06-28 11:27:18 -04:00
4018b3c533
poetry development
2023-06-28 11:17:08 -04:00
ecfb4abafb
simplify loading
2023-06-27 14:50:30 -04:00
2906cbab11
Update development.md
2023-06-27 14:07:31 -04:00
9d14e75185
Update development.md
2023-06-27 14:06:59 -04:00
a2745f8174
Update development.md
2023-06-27 14:06:49 -04:00
20cdd9fee6
update README.md
2023-06-27 13:51:20 -04:00
11614b6d84
add development doc
2023-06-27 13:46:46 -04:00
