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
1cde63dd64
Log unexpected server errors checking for update
...
This should unmask some failure modes that likely
show up in app logs as unmarshal errors
2024-02-27 09:17:04 -08:00
Jeffrey Morgan
5d7ea6616f
no extra disk space for windows installation ( #2739 )
2024-02-25 00:20:35 -05:00
Jeffrey Morgan
f58856bf6f
better directory cleanup in ollama.iss
2024-02-23 07:14:59 -05:00
Jeffrey Morgan
275ea01587
restore windows build flags and compression
2024-02-22 18:07:18 -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
Michael Yang
897b213468
use http.DefaultClient ( #2530 )
...
default client already handles proxy
2024-02-20 18:34:47 -05:00
Daniel Hiltgen
a497235a55
Fix view logs menu
2024-02-16 15:42:53 -08:00
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
117369aa73
Exit if we detect another copy of Ollama running
2024-02-15 14:58:29 -08:00
Daniel Hiltgen
5208cf09b1
clean up some logging
2024-02-15 14:56:55 -08:00
Daniel Hiltgen
bb9de6037c
Prevent multiple installers running concurrently
2024-02-15 14:56:55 -08:00
Michael Yang
86808f80a8
remove unused import
2024-02-15 12:09:11 -08:00
Michael Yang
4240b045e6
always enable view logs
2024-02-15 12:08:27 -08:00
Michael Yang
e547378893
disable default debug
2024-02-15 12:05:13 -08:00
Michael Yang
fd77dbec4d
do not print update request headers
2024-02-15 11:36:35 -08:00
Jeffrey Morgan
ed5489a96e
higher resolution tray icons
2024-02-14 22:55:03 -08:00
jmorganca
76113742cf
update installer title
2024-02-15 05:56:45 +00:00
Jeffrey Morgan
57e60c836f
better windows app and tray icons
2024-02-15 05:56:45 +00:00
jmorganca
622b1f3e67
update installer and app.exe metadata
2024-02-15 05:56:45 +00:00
jmorganca
7ad9844ac0
set exe metadata using resource files
2024-02-15 05:56:45 +00:00
Michael Yang
e43648afe5
rerefactor
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
cbfff4f868
update dependencies in app/
2023-10-19 15:52:41 -04:00
Jeffrey Morgan
832b4db9d4
Use correct url for auto updates
2023-10-13 19:04:42 -04:00
Bruce MacDonald
c43873f33b
check update response ( #785 )
2023-10-13 18:05:46 -04:00
Bruce MacDonald
3553d10769
check for newer updates ( #784 )
...
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2023-10-13 17:29:46 -04:00
Bruce MacDonald
24d82a23a2
do not download updates multiple times ( #633 )
2023-09-28 15:29:17 -04:00
Jeffrey Morgan
a5dbcf2e73
app: dont package ggml-metal.metal
2023-08-31 17:41:09 -04:00
Bruce MacDonald
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
Jeffrey Morgan
3d79b414d3
app: package ggml-metal.metal from correct directory
2023-08-17 23:55:45 -04:00
Jeffrey Morgan
4ab1da38ba
guard around id()
2023-08-10 14:11:54 -07:00
Jeffrey Morgan
76a678af34
app: dont always show installer window on top now that it lives in the dock
2023-08-10 09:53:46 -07:00
Jeffrey Morgan
6fbb380076
hide dock icon if window closes
2023-08-02 11:05:34 -04:00
Jeffrey Morgan
c75cafdb58
build for universal architecture on macos
2023-07-28 12:18:11 -04:00
Jeffrey Morgan
18b6b601ad
app: cleanup README.md
2023-07-28 10:51:41 -04:00
Jeffrey Morgan
0871083776
app: fix tray icon color scheme in dark mode
2023-07-28 07:03:46 -04:00
Jeffrey Morgan
dbb3174cbc
app: fix #218 and keep dock open on install
2023-07-27 10:53:38 -04:00
Jeffrey Morgan
31673d26d0
app: quit other instance when starting
2023-07-27 00:57:25 -04:00
Jeffrey Morgan
d0e934b497
app: tray cleanup
2023-07-26 14:24:56 -04:00
Jeffrey Morgan
e751e47d70
app: remove dialog, icons for updates
2023-07-26 14:04:36 -04:00
Jeffrey Morgan
c48f07f821
app: dont advance on error
2023-07-26 10:46:43 -04:00
Jeffrey Morgan
3f2a100465
app: log app errors to console
2023-07-25 15:42:04 -04:00
Eva Ho
9657314ae2
address comment
2023-07-21 17:29:07 -04:00
Eva Ho
3f7d2336c7
add prettier and address comments
2023-07-21 17:10:05 -04:00
Eva Ho
e0a73d7fbe
address comment
2023-07-21 16:53:56 -04:00
hoyyeva
b08c4ca2bd
Update app/src/index.ts
...
Co-authored-by: Jeffrey Morgan <251292+jmorganca@users.noreply.github.com>
2023-07-21 16:53:56 -04:00
Eva Ho
734892f1e2
address comment
2023-07-21 16:53:56 -04:00
Eva Ho
d2bfaeac63
format code
2023-07-21 16:53:56 -04:00
