baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
960 commits 1 branch 0 tags 14 MiB
Commit graph

960 commits

This branch
This branch
All branches
Author SHA1 Message Date
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
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
James Braza
94e1d96b29
Updated README section on community projects for table (#550) 2023-09-18 15:22:50 -04:00
Bruce MacDonald
66003e1d05
subprocess improvements (#524) 
* subprocess improvements

- increase start-up timeout
- when runner fails to start fail rather than timing out
- try runners in order rather than choosing 1 runner
- embed metal runner in metal dir rather than gpu
- refactor logging and error messages

* Update llama.go

* Update llama.go

* simplify by using glob
 2023-09-18 15:16:32 -04:00
Michael Yang
c345053a8b
Merge pull request #537 from jmorganca/mxyng/upload 
fix error on upload chunk
 2023-09-15 17:48:39 -07:00
Michael Yang
08d7c2a944 fix error on upload chunk 2023-09-15 15:59:30 -07:00
Michael Yang
bc9573dcb1
Merge pull request #530 from jmorganca/mxyng/progresswriter 
implement ProgressWriter
 2023-09-15 12:43:46 -07:00
Michael Yang
e53bc57d4d split uploadBlobChunked 2023-09-14 17:22:05 -07:00
Michael Yang
f0b398d17f implement ProgressWriter 2023-09-14 17:22:04 -07:00
Patrick Devine
8efbc5df55
DRAFT: add a simple python client to access ollama (#522) 2023-09-14 16:37:38 -07:00
Michael Yang
ccc3e9ac6d
Merge pull request #531 from jmorganca/mxyng/content-length 
set request.ContentLength
 2023-09-14 13:33:11 -07:00
Michael Yang
daa4f096f9 set request.ContentLength 
This informs the HTTP client the content length is known and disables
chunked Transfer-Encoding
 2023-09-14 13:32:44 -07:00
Michael Yang
3ee85f1c6c
Merge pull request #526 from jmorganca/mxyng/cleanup 
remove unused
 2023-09-14 13:10:59 -07:00
Bruce MacDonald
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
Michael Yang
83ffb154bc
Merge pull request #507 from jmorganca/mxyng/build 
update docker image
 2023-09-14 11:25:59 -07:00
Michael Yang
9aa192c812 update cuda docker image 2023-09-14 11:25:20 -07:00