Daniel Hiltgen
08600d5bec
CI subprocess path fix
2024-04-03 19:12:53 -07:00
Daniel Hiltgen
e4a7e5b2ca
Fix CI release glitches
...
The subprocess change moved the build directory
arm64 builds weren't setting cross-compilation flags when building on x86
2024-04-03 16:41:40 -07:00
Jeffrey Morgan
cd135317d2
Fix macOS builds on older SDKs ( #3467 )
2024-04-03 10:45:54 -07:00
Daniel Hiltgen
841adda157
Fix windows lint CI flakiness
2024-04-02 12:22:16 -07:00
Daniel Hiltgen
58d95cc9bd
Switch back to subprocessing for llama.cpp
...
This should resolve a number of memory leak and stability defects by allowing
us to isolate llama.cpp in a separate process and shutdown when idle, and
gracefully restart if it has problems. This also serves as a first step to be
able to run multiple copies to support multiple models concurrently.
2024-04-01 16:48:18 -07:00
Michael Yang
1ec0df1069
fix generate output
2024-04-01 13:47:34 -07:00
Jeffrey Morgan
06a1508bfe
Update 90_bug_report.yml
2024-03-29 10:11:17 -04:00
Daniel Hiltgen
97ae517fbf
Merge pull request #3398 from dhiltgen/release_latest
...
CI automation for tagging latest images
2024-03-28 16:25:54 -07:00
Daniel Hiltgen
44b813e459
Merge pull request #3377 from dhiltgen/rocm_v6_bump
...
Bump ROCm to 6.0.2 patch release
2024-03-28 16:07:54 -07:00
Daniel Hiltgen
539043f5e0
CI automation for tagging latest images
2024-03-28 16:07:37 -07:00
Daniel Hiltgen
c91a4ebcff
Bump ROCm to 6.0.2 patch release
2024-03-28 15:58:57 -07:00
Daniel Hiltgen
b79c7e4528
CI windows gpu builds
...
If we're doing generate, test windows cuda and rocm as well
2024-03-28 14:39:10 -07:00
Michael Yang
5255d0af8a
fix: workflows
2024-03-27 16:30:01 -07:00
Michael Yang
8838ae787d
stub stub
2024-03-27 13:59:12 -07:00
Michael Yang
db75402ade
mangle arch
2024-03-27 13:44:50 -07:00
Michael Yang
1e85a140a3
only generate on changes to llm subdirectory
2024-03-27 12:45:35 -07:00
Michael Yang
5b0c48d29e
only generate cuda/rocm when changes to llm detected
2024-03-27 12:23:09 -07:00
Daniel Hiltgen
f83e4db365
Switch runner for final release job
...
The manifest and tagging step use a lot of disk space
2024-03-25 20:51:40 -07:00
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
Blake Mizerany
8546dd3d72
.github: fix model and feature request yml ( #3155 )
2024-03-14 15:26:06 -07:00
Blake Mizerany
87100be5e0
.github: add issue templates ( #3143 )
2024-03-14 15:19:10 -07:00
Michael Yang
2cb74e23fb
fix ci
2024-03-07 11:33:49 -08:00
Daniel Hiltgen
3c8df3808b
Merge pull request #2885 from dhiltgen/rocm_v6_only
...
Revamp ROCm support
2024-03-07 10:51:00 -08:00
Michael Yang
72431031d9
no ci test on docs, examples
2024-03-07 10:44:48 -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
Jeffrey Morgan
d481fb3cc8
update go to 1.22 in other places ( #2975 )
2024-03-07 07:39:49 -08:00
Michael Yang
46c847c4ad
enable rocm builds
2024-02-06 13:36:13 -08:00
Michael Yang
92b1a21f79
use linux runners
2024-02-06 13:36:04 -08:00
Michael Yang
f06b99a461
disable rocm builds
2024-02-06 09:29:42 -08:00
Michael Yang
a8c5413d06
only generate gpu libs
2024-01-25 15:41:56 -08:00
Michael Yang
5580de4571
archive ollama binaries
2024-01-25 15:40:16 -08:00
Michael Yang
946431d5b0
build cuda and rocm
2024-01-25 15:40:15 -08:00
Michael Yang
0610126049
remove env setting
2024-01-25 15:39:43 -08:00
Michael Yang
8e5d359a03
stub generate outputs for lint
2024-01-24 17:36:10 -08:00
Michael Yang
e299831e2c
Merge pull request #1958 from purificant/ci
...
ci: update setup-go action
2024-01-18 14:53:36 -08:00
Daniel Hiltgen
ecbfc0182f
Go bump to v1.21 to pick up slog
2024-01-18 14:12:57 -08:00
Daniel Hiltgen
b992bf65fc
Disable arm64 for test phase
...
The runners are x86 so we can only run binaries that match.
2024-01-17 19:26:13 -08:00
Daniel Hiltgen
1b249748ab
Add multiple CPU variants for Intel Mac
...
This also refines the build process for the ext_server build.
2024-01-17 15:08:54 -08:00
Daniel Hiltgen
b3035112a1
Add macos cross-compile CI coverage
2024-01-14 10:38:59 -08:00
purificant
6a5bfc2ed6
update actions/setup-go
2024-01-12 22:27:25 +00:00
Michael Yang
997253143f
add lint and test on pull_request
2024-01-09 09:36:58 -08:00