Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Rebase ollama main #1

Closed
wants to merge 244 commits into from
Closed

Rebase ollama main #1

wants to merge 244 commits into from

Conversation

zhewang1-intc
Copy link
Owner

No description provided.

dhiltgen and others added 30 commits February 8, 2024 22:22
@dhiltgen
Shutdown faster
6680761 
Make sure that when a shutdown signal comes, we shutdown quickly instead
of waiting for a potentially long exchange to wrap up.
@jmorganca
patch: always add token to cache_tokens (ollama#2459)
26b13fc
@dhiltgen
Detect AMD GPU info via sysfs and block old cards
6d84f07 
This wires up some new logic to start using sysfs to discover AMD GPU
information and detects old cards we can't yet support so we can fallback to CPU mode.
@jmorganca
Check image filetype in api handlers (ollama#2467)
1f9078d
@dhiltgen
Merge pull request ollama#2465 from dhiltgen/block_rocm_pre_9
76b8728 
Detect AMD GPU info via sysfs and block old cards
@jmorganca
update submodule to 099afc6 (ollama#2468)
f76ca04
@dhiltgen
Merge pull request ollama#2422 from dhiltgen/better_kill
939c604 
More robust shutdown
@jmorganca
Fix issues with templating prompt in chat mode (ollama#2460)
48a273f
@lebrunel
Update README.md to include link to Ollama-ex Elixir library (ollama#…
1d26344 
…2477)
@bnorick
Fix infinite keep_alive (ollama#2480)
caf2b13
@jmorganca
bump submodule to 6c00a06 (ollama#2479)
2f9ed52
@jmorganca
Revert "bump submodule to 6c00a06 (ollama#2479)"
6920964 
This reverts commit 2f9ed52.
@jmorganca
set shutting_down to false once shutdown is complete (ollama#2484)
f7231ad
@jmorganca
Revert "Revert "bump submodule to 6c00a06 (ollama#2479)"" (ollama#2485
9241a29 
)

This reverts commit 6920964.
@pdevine
handle race condition while setting raw mode in windows (ollama#2509)
42e77e2
@dhiltgen @jmorganca
Move Mac App to a new dir
9da9e8f
@dhiltgen @jmorganca
Move hub auth out to new package
f397e0e
@dhiltgen @jmorganca
Implement new Go based Desktop app
29e90cc 
This focuses on Windows first, but coudl be used for Mac
and possibly linux in the future.
@vinjn @jmorganca
Import "containerd/console" lib to support colorful output in Windows…
66ef308 
… terminal
@dhiltgen @jmorganca
Fix lint error on ignored error for win console
823a520
@mxyng @jmorganca
rerefactor
e43648a
@jmorganca
set exe metadata using resource files
7ad9844
@jmorganca
update installer and app.exe metadata
622b1f3
@jmorganca
better windows app and tray icons
57e60c8
@jmorganca
update installer title
7611374
@jmorganca
higher resolution tray icons
ed5489a
@mchiang0610
Update README.md
fefb3e7
@mxyng
do not print update request headers
fd77dbe
@mxyng
disable default debug
e547378
@mxyng
always enable view logs
4240b04
dhiltgen and others added 27 commits March 14, 2024 18:00
@dhiltgen
Add ROCm support to linux install script (ollama#2966)
6459377
@bmizerany
server: replace blob prefix separator from ':' to '-' (ollama#3146)
703684a 
This fixes issues with blob file names that contain ':' characters to be rejected by file systems that do not support them.
@bmizerany @jmorganca
llm,readline: use errors.Is instead of simple == check (ollama#3161)
6ce37e4 
This fixes some brittle, simple equality checks to use errors.Is. Since
go1.13, errors.Is is the idiomatic way to check for errors.

Co-authored-by: Jeffrey Morgan <[email protected]>
@dhiltgen
Wire up more complete CI for releases
540f4af 
Flesh out our github actions CI so we can build official releaes.
@dhiltgen
Add Radeon gfx940-942 GPU support
d4c10df
@dhiltgen
Merge pull request ollama#3171 from dhiltgen/rocm_94x
052b5a3 
Add Radeon gfx940-942 GPU support
@dhiltgen
Merge pull request ollama#3086 from dhiltgen/import_server
6ad414f 
Import server.cpp to retain llava support
@dhiltgen
Merge pull request ollama#3028 from ollama/ci_release
ab34562 
CI release process
@dhiltgen
Merge pull request ollama#3111 from alitrack/main
f4b31c2 
Update ollama.iss
@jmorganca
add llm/ext_server directory to linguist-vendored (ollama#3173)
2dce1ab
@jmorganca
llama: remove server static assets (ollama#3174)
e95ffc7
@mxyng
Merge pull request ollama#3083 from ollama/mxyng/refactor-readseeker
22f3264 
refactor readseeker
@mxyng
dyn global
3c4ad0e
@mxyng
Merge pull request ollama#3217 from ollama/mxyng/cleanup
01cff61 
remove global
@jmorganca
update faq.md
2297ad3
@jmorganca
Update faq.md
7ed3e94
@felipeagc @zhewang1-intc
Build llama.cpp with SYCL support
a4bc1de
@felipeagc @zhewang1-intc
Add gpu_info_oneapi
24242d4
@felipeagc @zhewang1-intc
Add oneapi to gpu.go
76c8080
@felipeagc @zhewang1-intc
Fix oneAPI linking by using icx compiler and updating rpath
a261573
@felipeagc @zhewang1-intc
Add oneAPI integrated GPU detection
db05e58
@felipeagc @zhewang1-intc
Update rocky linux gcc version (rocky linux 9 only has gcc 12+)
ac90517
@felipeagc @zhewang1-intc
Add oneapi docker build
b2096c4
@zhewang1-intc
update llama.cpp
6462d77
@zhewang1-intc
fix ollama compile
892a74f
@zhewang1-intc
Merge branch 'main' into rebase_ollama_main
d815e78
@zhewang1-intc
fix lint & compile
1b4fe85
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.