Commit graph

1774 commits

Author SHA1 Message Date
Patrick Devine
b5614f3ebc
fix end-of-line issue with the new prompt (#582) 2023-09-23 17:20:30 -07:00
Jeffrey Morgan
8b2ba9cab8 minor improvements to install.sh 2023-09-23 11:20:39 -04:00
Jeffrey Morgan
e29662ab5c fix minor install script issues on debian 2023-09-23 10:25:47 -04:00
Bruce MacDonald
cbc40aa996
debian installer support (#579)
* debian installer support

- normalize os name to lowercase
- check needed commands are available
- dont check sudo when root user
- share common install commands
- support debian cuda install
- skip aarm cuda install
- system user shared home dir

* refactor and add other platforms (#580)

---------

Co-authored-by: Michael Yang <mxyng@pm.me>
2023-09-23 09:46:47 -04:00
Jeffrey Morgan
5cb82540c9 install.sh: update install url 2023-09-23 09:35:14 -04:00
Jeffrey Morgan
d7849a1dc9 add .env to .dockerignore 2023-09-23 00:53:48 -04:00
Jeffrey Morgan
01c44d687e add multi line strings to final prompt 2023-09-23 00:27:24 -04:00
Jeffrey Morgan
9b12a511ca check other request fields before load short circuit in /api/generate 2023-09-22 23:50:55 -04:00
Jeffrey Morgan
e20362e0d5 fix multi line input in ollama run 2023-09-22 23:49:35 -04:00
Patrick Devine
c928ceb927
add word wrapping for lines which are longer than the terminal width (#553) 2023-09-22 13:36:08 -07:00
Michael Yang
e1a0846483
Merge pull request #571 from jmorganca/mxyng/update-dockerfile
update dockerfile.cuda
2023-09-22 12:34:41 -07:00
Jeffrey Morgan
f997e29e45
Add Dockerfile.build for building linux binaries (#558)
Add `Dockerfile.build` for building linux binaries

---------

Co-authored-by: Michael Yang <mxyng@pm.me>
2023-09-22 15:20:12 -04:00
Patrick Devine
87d9efb364
switch to forked readline lib which doesn't wreck the repl prompt (#578) 2023-09-22 12:17:45 -07:00
Michael Yang
93d3a2568d replace dockerfile 2023-09-22 11:57:38 -07:00
Michael Yang
5a81390b24 update dockerfile.cuda 2023-09-22 11:57:38 -07:00
Michael Yang
a89ef99aed
Merge pull request #575 from jmorganca/mxyng/fix-ipv6-only
fix ipv6 parse ip
2023-09-22 11:47:11 -07:00
Bruce MacDonald
dc0c725ceb
ubuntu cuda drivers (#576) 2023-09-22 19:43:14 +01:00
Bruce MacDonald
5d71bda478
close llm on interrupt (#577) 2023-09-22 19:41:52 +01:00
Michael Yang
88897a90e4 fix ipv6 parse ip 2023-09-22 10:41:32 -07:00
Bruce MacDonald
9df31c3518
linux installer script (#534)
Co-authored-by: Michael Yang <mxyng@pm.me>
2023-09-22 17:01:03 +01:00
Michael Yang
2044f9d4da
Merge pull request #570 from jmorganca/mxyng/head-request
fix HEAD request
2023-09-21 16:56:17 -07:00
Michael Yang
0d186f3b33
Merge pull request #569 from jmorganca/mxyng/update-submodules
silence warm up log
2023-09-21 16:52:42 -07:00
Michael Yang
82f5b66c01 register HEAD /api/tags 2023-09-21 16:38:03 -07:00
Michael Yang
c986694367 fix HEAD / request
HEAD request should respond like their GET counterparts except without a
response body.
2023-09-21 16:35:58 -07:00
Michael Yang
058d0cd04b silence warm up log 2023-09-21 14:53:33 -07:00
Michael Yang
ee1c994d15
update submodule (#567) 2023-09-21 16:22:23 -04:00
Bruce MacDonald
4cba75efc5
remove tmp directories created by previous servers (#559)
* remove tmp directories created by previous servers

* clean up on server stop

* Update routes.go

* Update server/routes.go

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* create top-level temp ollama dir

* check file exists before creating

---------

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
Co-authored-by: Michael Yang <mxyng@pm.me>
2023-09-21 20:38:49 +01:00
Michael Yang
8c83701e9f
Merge pull request #566 from jmorganca/mxyng/api-check-model-exists
Use API to check if model exists and pull if necessary
2023-09-21 10:35:14 -07:00
Michael Yang
6137b12799 validate existence and pull model using api 2023-09-21 09:55:34 -07:00
Michael Yang
1fabba474b refactor default allow origins
this should be less error prone
2023-09-21 09:42:25 -07:00
Michael Yang
765770efdb
Merge pull request #562 from jmorganca/mxyng/fix-ollama-host
fix OLLAMA_HOST parsing for ip6
2023-09-20 19:54:47 -07:00
Michael Yang
9297ff8330 fix OLLAMA_HOST parsing for ip6 2023-09-20 18:52:57 -07:00
Michael Yang
ee4fd16f2c
Merge pull request #556 from jmorganca/pack-cuda
pack in cuda libs
2023-09-20 15:02:36 -07:00
Michael Yang
a9ed7cc6aa rename generate.go 2023-09-20 14:42:17 -07:00
Michael Yang
6c6a31a1e8 embed libraries using cmake 2023-09-20 14:41:57 -07:00
Bruce MacDonald
fc6ec356fc remove libcuda.so 2023-09-20 20:36:14 +01:00
Bruce MacDonald
1255bc9b45 only package 11.8 runner 2023-09-20 20:00:41 +01:00
Michael Yang
084e4c782a
Merge pull request #557 from jmorganca/mxyng/cleanup
fix impossible condition
2023-09-20 11:51:01 -07:00
Michael Yang
58ffa03d8b fix impossible condition 2023-09-20 11:27:44 -07:00
Michael Yang
637f8bc6a5
Merge pull request #536 from jmorganca/mxyng/redirect-uploads
explicitly follow upload redirects
2023-09-20 11:27:03 -07:00
Michael Yang
499e9007a5 pick chunksize based on location 2023-09-20 11:10:24 -07:00
Bruce MacDonald
b9bb5ca288 use cuda_version 2023-09-20 17:58:16 +01:00
Bruce MacDonald
4e8be787c7 pack in cuda libs 2023-09-20 17:40:42 +01:00
Michael Yang
aa45d7c1df draft: explicitly follow upload redirects 2023-09-19 13:36:58 -07:00
Michael Yang
e35565c567
Merge pull request #555 from jmorganca/mxyng/fix-windows-startup
fix build
2023-09-19 10:51:58 -07:00
Michael Yang
a5520bfb42 fix build 2023-09-19 10:42:24 -07:00
Michael Yang
2627c464ba
Merge pull request #554 from jmorganca/mxyng/fix-windows-startup
fix mkdir on windows
2023-09-19 09:42:12 -07:00
Michael Yang
b58d5d16b0 fix mkdir on windows 2023-09-19 09:41:13 -07:00
Patrick Devine
24580df958
only add a layer if there is actual data (#535) 2023-09-18 13:47:45 -07:00
Patrick Devine
80dd44e80a
Cmd changes (#541) 2023-09-18 12:26:56 -07:00