baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
3586 commits 1 branch 0 tags 14 MiB
Commit graph

315 commits

Author SHA1 Message Date
Jeffrey Morgan
a0b8a32eb4
Terminate subprocess if receiving SIGINT or SIGTERM signals while model is loading (#3653) 
* terminate subprocess if receiving `SIGINT` or `SIGTERM` signals while model is loading

* use `unload` in signal handler
 2024-04-15 12:09:32 -04:00
Michael Yang
9502e5661f cgo quantize 2024-04-08 15:31:08 -07:00
Michael Yang
e1c9a2a00f no blob create if already exists 2024-04-08 15:09:48 -07:00
Daniel Hiltgen
6589eb8a8c Revert options as a ref in the server 2024-04-02 16:44:10 -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
91b3e4d282 update memory calcualtions 
count each layer independently when deciding gpu offloading
 2024-04-01 13:16:32 -07:00
Michael Yang
af8a8a6b59 fix: trim quotes on OLLAMA_ORIGINS 2024-03-27 15:24:29 -07:00
Patrick Devine
1b272d5bcd
change github.com/jmorganca/ollama to github.com/ollama/ollama (#3347) 2024-03-26 13:04:17 -07:00
Blake Mizerany
703684a82a
server: replace blob prefix separator from ':' to '-' (#3146) 
This fixes issues with blob file names that contain ':' characters to be rejected by file systems that do not support them.
 2024-03-14 20:18:06 -07:00
Patrick Devine
47cfe58af5
Default Keep Alive environment variable (#3094) 
---------

Co-authored-by: Chris-AS1 <8493773+Chris-AS1@users.noreply.github.com>
 2024-03-13 13:29:40 -07:00
Daniel Hiltgen
4a5c9b8035 Finish unwinding idempotent payload logic 
The recent ROCm change partially removed idempotent
payloads, but the ggml-metal.metal file for mac was still
idempotent.  This finishes switching to always extract
the payloads, and now that idempotentcy is gone, the
version directory is no longer useful.
 2024-03-09 08:34:39 -08:00
Jeffrey Morgan
5b3fad9636 separate out isLocalIP 2024-03-09 00:22:08 -08:00
Jeffrey Morgan
bfec2c6e10 simplify host checks 2024-03-08 23:29:53 -08:00
Jeffrey Morgan
5c143af726 add additional allowed hosts 2024-03-08 23:23:59 -08:00
Jeffrey Morgan
fc8c044584
add allowed host middleware and remove workDir middleware (#3018) 2024-03-08 22:23:47 -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
3b4bab3dc5
Fix embeddings load model behavior (#2848) 2024-02-29 17:40:56 -08:00
Michael Yang
0e19476b56
prepend image tags (#2789) 
instead of appending image tags, prepend them - this generally produces better results
 2024-02-29 11:30:14 -08:00
Jeffrey Morgan
287ba11500 better error message when calling /api/generate or /api/chat with embedding models 2024-02-20 21:53:45 -05:00
Jeffrey Morgan
63861f58cc
Support for bert and nomic-bert embedding models 2024-02-20 21:37:29 -05:00
Bruce MacDonald
88622847c6
fix: chat system prompting overrides (#2542) 2024-02-16 14:42:43 -05:00
Michael Yang
e43648afe5 rerefactor 2024-02-15 05:56:45 +00:00
Daniel Hiltgen
f397e0e988 Move hub auth out to new package 2024-02-15 05:56:45 +00:00
Jeffrey Morgan
48a273f80b
Fix issues with templating prompt in chat mode (#2460) 2024-02-12 15:06:57 -08:00
Jeffrey Morgan
1f9078d6ae
Check image filetype in api handlers (#2467) 2024-02-12 11:16:20 -08:00
Jeffrey Morgan
a0a199b108
Fix hanging issue when sending empty content (#2399) 2024-02-07 19:30:33 -05:00
Jeffrey Morgan
453f572f83
Initial OpenAI /v1/chat/completions API compatibility (#2376) 2024-02-07 17:24:29 -05:00
Michael Yang
bfbf2f7cf7
Merge pull request #2296 from ollama/mxyng/img-tags 
append image tags to user content
 2024-02-01 13:16:59 -08:00
Michael Yang
3d6f48507a structured debug prompt 2024-02-01 11:56:28 -08:00
Michael Yang
d125510b4b remove image tags 2024-02-01 11:32:51 -08:00
Michael Yang
fb56988014 account for image projection in token count 2024-02-01 09:50:48 -08:00
Michael Yang
d046bee790 use llm.ImageData for chat 2024-01-31 19:18:25 -08:00
Jeffrey Morgan
f11bf0740b use llm.ImageData 2024-01-31 19:13:48 -08:00
Michael Yang
8450bf66e6 trim images 2024-01-31 19:13:47 -08:00
Michael Yang
b4e11be8ef append image tags to user content 2024-01-31 19:13:10 -08:00
Michael Yang
8ac08a0eec update slog handler options 
- consistent format by using text handler for debug and non-debug
- truncate source file to just the file name
 2024-01-31 15:15:00 -08:00
Bruce MacDonald
0632dff3f8
trim chat prompt based on llm context size (#1963) 2024-01-30 15:59:29 -05:00
Jeffrey Morgan
f2245c7c77
print prompt with OLLAMA_DEBUG=1 (#2245) 2024-01-28 15:22:35 -08:00
Jeffrey Morgan
e4b9b72f2a
Do not repeat system prompt for chat templating (#2241) 2024-01-28 14:15:56 -08:00
Patrick Devine
b5cf31b460
add keep_alive to generate/chat/embedding api endpoints (#2146) 2024-01-26 14:28:02 -08:00
Patrick Devine
7c40a67841
Save and load sessions (#2063) 2024-01-25 12:12:36 -08:00
Michael Yang
aac9ab4db7 fix show handler 2024-01-18 15:36:50 -08:00
Michael Yang
745b5934fa add model to ModelResponse 2024-01-18 14:32:55 -08:00
Michael Yang
a38d88d828 api: add model for all requests 
prefer using req.Model and fallback to req.Name
 2024-01-18 14:31:37 -08:00
Daniel Hiltgen
fedd705aea Mechanical switch from log to slog 
A few obvious levels were adjusted, but generally everything mapped to "info" level.
 2024-01-18 14:12:57 -08:00
Patrick Devine
eef50accb4
Fix show parameters (#2017) 2024-01-16 10:34:44 -08:00
Michael Yang
2b9892a808 fix(windows): modelpath and list 2024-01-09 09:36:58 -08:00
Michael Yang
2bb2bdd5d4 fix lint 2024-01-09 09:36:58 -08:00
Michael Yang
acfc376efd add .golangci.yaml 2024-01-09 09:36:58 -08:00
Michael Yang
0101e76dbe
Merge pull request #1797 from sublimator/nd-allow-extension-origins-still-needs-explicit-listing-2024-01-05 
fix: allow extension origins (still needs explicit listing), fixes #1686
 2024-01-05 17:20:09 -08:00
Patrick Devine
22e93efa41 add show info command and fix the modelfile 2024-01-05 12:20:05 -08:00
Nicholas Dudfield
8baaaa39c0 Allow extension origins (still needs explicit listing), fixes #1686 2024-01-05 09:06:47 +07:00
Bruce MacDonald
0b3118e0af
fix: relay request opts to loaded llm prediction (#1761) 2024-01-03 12:01:42 -05:00
Bruce MacDonald
db356c8519
post-response templating (#1427) 2023-12-22 17:07:05 -05:00
Daniel Hiltgen
35934b2e05 Adapted rocm support to cgo based llama.cpp 2023-12-19 09:05:46 -08:00
Daniel Hiltgen
d4cd695759 Add cgo implementation for llama.cpp 
Run the server.cpp directly inside the Go runtime via cgo
while retaining the LLM Go abstractions.
 2023-12-19 09:05:46 -08:00
Bruce MacDonald
811b1f03c8 deprecate ggml 
- remove ggml runner
- automatically pull gguf models when ggml detected
- tell users to update to gguf in the case automatic pull fails

Co-Authored-By: Jeffrey Morgan <jmorganca@gmail.com>
 2023-12-19 09:05:46 -08:00
Bruce MacDonald
d99fa6ce0a
send empty messages on last chat response (#1530) 2023-12-18 14:23:38 -05:00
Patrick Devine
630518f0d9
Add unit test of API routes (#1528) 2023-12-14 16:47:40 -08:00
Bruce MacDonald
6ee8c80199
restore model load duration on generate response (#1524) 
* restore model load duration on generate response

- set model load duration on generate and chat done response
- calculate createAt time when response created

* remove checkpoints predict opts

* Update routes.go
 2023-12-14 12:15:50 -05:00
Patrick Devine
d9e60f634b
add image support to the chat api (#1490) 2023-12-12 13:28:58 -08:00
Patrick Devine
910e9401d0
Multimodal support (#1216) 
---------

Co-authored-by: Matt Apperson <mattapperson@Matts-MacBook-Pro.local>
 2023-12-11 13:56:22 -08:00
Jeffrey Morgan
7db5bcf73b fix go-staticcheck warning 2023-12-10 11:44:27 -05:00
Jeffrey Morgan
fa2f095bd9 fix model name returned by /api/generate being different than the model name provided 2023-12-10 11:42:15 -05:00
Jeffrey Morgan
045b855db9 fix error on accumulating final chat response 2023-12-10 11:24:39 -05:00
Jeffrey Morgan
32064a0646 fix empty response when receiving runner error 2023-12-10 10:53:38 -05:00
Jeffrey Morgan
9e1406e4ed Don't expose model information in /api/generate 2023-12-09 02:05:43 -08:00
Bruce MacDonald
7e9405fd07
fix: encode full previous prompt in context (#1424) 2023-12-08 16:53:51 -05:00
Michael Yang
c3ff36088b
Merge pull request #774 from jmorganca/mxyng/server-version 
add version api and show server version in cli
 2023-12-06 13:22:55 -08:00
Michael Yang
5d75505ebd return model configuration in generate 2023-12-05 14:39:02 -08:00
Michael Yang
b9495ea162 load projectors 2023-12-05 14:36:12 -08:00
Michael Yang
d3479c07a1
Merge pull request #1250 from jmorganca/mxyng/create-layer 
refactor layer creation
 2023-12-05 14:32:52 -08:00
Bruce MacDonald
195e3d9dbd
chat api endpoint (#1392) 2023-12-05 14:57:33 -05:00
Michael Yang
1ebdbd9694 server: add version handler 2023-12-05 09:36:01 -08:00
Jeffrey Morgan
00d06619a1 Revert "chat api (#991)" while context variable is fixed 
This reverts commit 7a0899d62d.
 2023-12-04 21:16:27 -08:00
Michael Yang
a3737cbd33 use NewLayer for CreateBlobHandler 2023-12-04 16:59:23 -08:00
Bruce MacDonald
7a0899d62d
chat api (#991) 
- update chat docs
- add messages chat endpoint
- remove deprecated context and template generate parameters from docs
- context and template are still supported for the time being and will continue to work as expected
- add partial response to chat history
 2023-12-04 18:01:06 -05:00
Bruce MacDonald
96122b7271
validate model tags on copy (#1323) 2023-11-29 15:54:29 -05:00
Timothy Jaeryang Baek
c2e3b89176
fix: disable ':' in tag names (#1280) 
Co-authored-by: rootedbox
 2023-11-29 13:33:45 -05:00
Bruce MacDonald
37d95157df
fix relative path on create (#1222) 2023-11-21 15:43:17 -05:00
Bruce MacDonald
43a726149d fix potentially inaccurate error message 2023-11-18 21:25:07 -05:00
Jeffrey Morgan
bab9494176 add - separator to temp file created on ollama create 2023-11-18 09:39:52 -05:00
Michael Yang
c6e6c8ee7e fix cross device rename 2023-11-17 15:22:17 -08:00
Michael Yang
54f92f01cb update docs 2023-11-15 15:28:15 -08:00
Michael Yang
bc22d5a38b no blob response 2023-11-15 15:16:23 -08:00
Michael Yang
1901044b07 use checksum reference 2023-11-15 15:16:23 -08:00
Michael Yang
1552cee59f client create modelfile 2023-11-15 15:16:23 -08:00
Michael Yang
3ca56b5ada add create modelfile field 2023-11-15 15:16:23 -08:00
Michael Yang
b0d14ed51c refactor create model 2023-11-15 15:16:23 -08:00
Jeffrey Morgan
5cba29b9d6
JSON mode: add `"format" as an api parameter (#1051) 
* add `"format": "json"` as an API parameter
---------
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-11-09 16:44:02 -08:00
Bruce MacDonald
ec2a31e9b3
support raw generation requests (#952) 
- add the optional `raw` generate request parameter to bypass prompt formatting and response context
-add raw request to docs
 2023-11-08 14:05:02 -08:00
Noah Gitsham
8ae8c9fa8c
Remove duplicate "install" in GPU support warning (#984) 2023-11-03 00:45:14 -07:00
Noah Gitsham
f39daff461
Add missing "be" to GPU support warning message (#983) 2023-11-02 18:37:12 -07:00
Michael Yang
2c6189f4fe
Merge pull request #750 from jmorganca/mxyng/concurrent-uploads 
concurrent uploads
 2023-11-01 15:00:01 -07:00
Bruce MacDonald
f9a4281124
clean up: remove server functions from client (#937) 2023-10-30 11:10:18 -04:00
Michael Yang
4e09aab8b9 concurrent uploads 2023-10-27 17:07:33 -07:00
Michael Yang
386169205c
update runtime options (#864) 2023-10-20 21:17:14 -04:00
Jeffrey Morgan
7ed5a39bc7 simpler check for model loading compatibility errors 2023-10-19 14:50:49 -04:00
Michael Yang
e1c5be24e7 check json eof 2023-10-19 09:21:51 -07:00
Michael Yang
2ad8a074ac generate: set created_at 
move the empty response so it's more visible
 2023-10-19 09:21:51 -07:00
Michael Yang
7e547c6833 s/message/error/ 2023-10-19 09:21:04 -07:00
Michael Yang
689842b9ff request: bad request when model missing fields 2023-10-19 09:21:04 -07:00
Michael Yang
a19d47642e models: rm workDir from CreateModel 
unused after removing EMBED
 2023-10-19 09:21:04 -07:00
Bruce MacDonald
fe6f3b48f7
do not reload the running llm when runtime params change (#840) 
- only reload the running llm if the model has changed, or the options for loading the running model have changed
- rename loaded llm to runner to differentiate from loaded model image
- remove logic which keeps the first system prompt in the generation context
 2023-10-19 10:39:58 -04:00
Yiorgis Gozadinos
8c6c2cbc8c When the .ollama folder is broken or there are no models return an empty list on /api/tags 2023-10-18 08:23:20 +02:00
Michael Yang
1af493c5a0 server: print version on start 2023-10-16 09:59:14 -07:00
Bruce MacDonald
a0c3e989de
deprecate modelfile embed command (#759) 2023-10-16 11:07:37 -04:00
Bruce MacDonald
7804b8fab9
validate api options fields from map (#711) 2023-10-12 11:18:11 -04:00
Bruce MacDonald
274d5a5fdf
optional parameter to not stream response (#639) 
* update streaming request accept header
* add optional stream param to request bodies
 2023-10-11 12:54:27 -04:00
Bruce MacDonald
af4cf55884
not found error before pulling model (#718) 2023-10-06 16:06:20 -04:00
Jay Nakrani
1d0ebe67e8
Document response stream chunk delimiter. (#632) 
Document response stream chunk delimiter.
 2023-09-29 21:45:52 -07:00
Bruce MacDonald
a1b2d95f96
remove unused push/pull params (#650) 2023-09-29 17:27:19 -04:00
Michael Yang
8608eb4760 prune empty directories 2023-09-27 10:58:09 -07:00
Jeffrey Morgan
9b12a511ca check other request fields before load short circuit in /api/generate 2023-09-22 23:50:55 -04:00
Bruce MacDonald
5d71bda478
close llm on interrupt (#577) 2023-09-22 19:41:52 +01:00
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
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
1fabba474b refactor default allow origins 
this should be less error prone
 2023-09-21 09:42:25 -07:00
Bruce MacDonald
1255bc9b45 only package 11.8 runner 2023-09-20 20:00:41 +01:00
Patrick Devine
80dd44e80a
Cmd changes (#541) 2023-09-18 12:26:56 -07:00
Bruce MacDonald
f221637053
first pass at linux gpu support (#454) 
* linux gpu support
* handle multiple gpus
* add cuda docker image (#488)
---------

Co-authored-by: Michael Yang <mxyng@pm.me>
 2023-09-12 11:04:35 -04:00
Patrick Devine
e7e91cd71c
add autoprune to remove unused layers (#491) 2023-09-11 11:46:35 -07:00
Patrick Devine
790d24eb7b
add show command (#474) 2023-09-06 11:04:17 -07:00
Michael Yang
681f3c4c42 fix num_keep 2023-09-03 17:47:49 -04:00
Michael Yang
eeb40a672c fix list models for windows 2023-08-31 09:47:10 -04:00
Michael Yang
0f541a0367 s/ListResponseModel/ModelResponse/ 2023-08-31 09:47:10 -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
Patrick Devine
8bbff2df98
add model IDs (#439) 2023-08-28 20:50:24 -07:00
Michael Yang
95187d7e1e build release mode 2023-08-22 09:52:43 -07:00
Jeffrey Morgan
a9f6c56652 fix FROM instruction erroring when referring to a file 2023-08-22 09:39:42 -07:00
Ryan Baker
0a892419ad
Strip protocol from model path (#377) 2023-08-21 21:56:56 -07:00
Bruce MacDonald
326de48930 use loaded llm for embeddings 2023-08-15 10:50:54 -03:00
Patrick Devine
d9cf18e28d
add maximum retries when pushing (#334) 2023-08-11 15:41:55 -07:00
Michael Yang
6517bcc53c
Merge pull request #290 from jmorganca/add-adapter-layers 
implement loading ggml lora adapters through the modelfile
 2023-08-10 17:23:01 -07:00
Michael Yang
6a6828bddf
Merge pull request #167 from jmorganca/decode-ggml 
partial decode ggml bin for more info
 2023-08-10 17:22:40 -07:00
Jeffrey Morgan
040a5b9750 clean up cli flags 2023-08-10 09:27:03 -07:00
Michael Yang
6de5d032e1 implement loading ggml lora adapters through the modelfile 2023-08-10 09:23:39 -07:00
Michael Yang
fccf8d179f partial decode ggml bin for more info 2023-08-10 09:23:10 -07:00
Bruce MacDonald
4b3507f036 embeddings endpoint 
Co-Authored-By: Jeffrey Morgan <jmorganca@gmail.com>
 2023-08-10 11:45:57 -04:00
Bruce MacDonald
868e3b31c7 allow for concurrent pulls of the same files 2023-08-09 11:31:54 -04:00
Bruce MacDonald
09d8bf6730 fix build errors 2023-08-09 10:45:57 -04:00
Bruce MacDonald
7a5f3616fd
embed text document in modelfile 2023-08-09 10:26:19 -04:00
Jeffrey Morgan
cff002b824 use content type application/x-ndjson for streaming responses 2023-08-08 21:38:10 -07:00
Jeffrey Morgan
a027a7dd65 add 0.0.0.0 as an allowed origin by default 
Fixes #282
 2023-08-08 13:39:50 -07:00
Bruce MacDonald
21ddcaa1f1 pr comments 
- default to embeddings enabled
- move embedding logic for loaded model to request
- allow embedding full directory
- close llm on reload
 2023-08-08 13:49:37 -04:00
Michael Yang
f2074ed4c0
Merge pull request #306 from jmorganca/default-keep-system 
automatically set num_keep if num_keep < 0
 2023-08-08 09:25:34 -07:00
Bruce MacDonald
a6f6d18f83 embed text document in modelfile 2023-08-08 11:27:17 -04:00
Michael Yang
4dc5b117dd automatically set num_keep if num_keep < 0 
num_keep defines how many tokens to keep in the context when truncating
inputs. if left to its default value of -1, the server will calculate
num_keep to be the left of the system instructions
 2023-08-07 16:19:12 -07:00
cmiller01
fb593b7bfc pass flags to serve to allow setting allowed-origins + host and port 
* resolves: https://github.com/jmorganca/ollama/issues/300 and
https://github.com/jmorganca/ollama/issues/282

* example usage:
```
ollama serve --port 9999 --allowed-origins "http://foo.example.com,http://192.0.0.1"
```
 2023-08-07 03:34:37 +00:00