Commit graph

570 commits

Author SHA1 Message Date
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
Patrick Devine
3b6a9154dd
Simplify model conversion (#3422) 2024-04-01 16:14:53 -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
d338d70492 refactor model parsing 2024-04-01 13:16:15 -07:00
Patrick Devine
5a5efee46b
Add gemma safetensors conversion (#3250)
Co-authored-by: Michael Yang <mxyng@pm.me>
2024-03-28 18:54:01 -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
Daniel Hiltgen
949b6c01e0 Revamp go based integration tests
This uplevels the integration tests to run the server which can allow
testing an existing server, or a remote server.
2024-03-23 14:24:18 +01:00
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
Michael Yang
76bdebbadf decode ggla 2024-03-08 15:46:25 -08:00
Bruce MacDonald
0cebc79cba
fix: allow importing a model from name reference (#3005) 2024-03-08 12:27:47 -05:00
Jeffrey Morgan
fc06205971
Revert "adjust download and upload concurrency based on available bandwidth" (#2995) 2024-03-07 18:10:16 -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
Michael Yang
2e20110e50
Merge pull request #2221 from ollama/mxyng/up-down-ccy
adjust download and upload concurrency based on available bandwidth
2024-03-07 09:27:33 -08:00
Patrick Devine
2c017ca441
Convert Safetensors to an Ollama model (#2824) 2024-03-06 21:01:51 -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
Michael Yang
084d846621 refactor 2024-02-21 13:42:48 -08:00
Michael Yang
6a4b994433 lint 2024-02-21 13:42:48 -08:00
Michael Yang
bea007deb7 use LimitGroup for uploads 2024-02-21 13:42:48 -08:00
Michael Yang
074934be03 adjust group limit based on download speed 2024-02-21 13:42:48 -08:00
Michael Yang
0de12368a0 add new LimitGroup for dynamic concurrency 2024-02-21 13:42:48 -08:00
Michael Yang
917bd61084 refactor download run 2024-02-21 13:42:46 -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
Michael Yang
210b65268e
replace strings buffer with hasher (#2437)
the buffered value is going into the hasher eventually so write directly
to the hasher instead
2024-02-20 19:07:50 -05:00
Michael Yang
897b213468
use http.DefaultClient (#2530)
default client already handles proxy
2024-02-20 18:34:47 -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
e805ac1d59 fix response on token error 2024-02-07 11:05:49 -08:00
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
f3761405c8 use image id 2024-02-01 11:52:42 -08:00
Michael Yang
e49dc9f3d8 fix tests 2024-02-01 11:48:11 -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
Bruce MacDonald
a896079705
preserve last system message from modelfile (#2289) 2024-01-31 21:45:01 -05:00
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
Michael Yang
c8b1f2369e remove unnecessary parse raw 2024-01-30 17:00:53 -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
Michael Yang
9d3dcfd0ec fix logging 2024-01-26 11:04:27 -08:00
Michael Yang
6e0ea5ecc8
Merge pull request #1916 from ollama/mxyng/inactivity-monitor
download: add inactivity monitor
2024-01-26 10:56:00 -08:00
Patrick Devine
7c40a67841
Save and load sessions (#2063) 2024-01-25 12:12:36 -08:00
Michael Yang
c08dfaa23d fix: remove overwritten model layers
if create overrides a manifest, first add the older manifest's layers to
the delete map so they can be cleaned up
2024-01-19 14:58:37 -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
Michael Yang
96cfb62641 fix: normalize name path before splitting 2024-01-16 16:48:29 -08:00
Patrick Devine
eef50accb4
Fix show parameters (#2017) 2024-01-16 10:34:44 -08:00
Michael Yang
27331ae3a8 download: add inactivity monitor
if a download part is inactive for some time, restart it
2024-01-12 15:23:15 -08:00
Michael Yang
cf29bd2d72 fix: request retry with error
this fixes a subtle bug with makeRequestWithRetry where an HTTP status
error on a retried request will potentially not return the right err
2024-01-12 13:32:27 -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
Bruce MacDonald
7e8f7c8358
remove ggml automatic re-pull (#1856) 2024-01-08 14:41:01 -05:00
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
4ad6c9b11f
fix: pull either original model or from model on create (#1774) 2024-01-04 01:34:38 -05:00
Bruce MacDonald
0b3118e0af
fix: relay request opts to loaded llm prediction (#1761) 2024-01-03 12:01:42 -05:00
Daniel Hiltgen
697bea6939 Guard integration tests with a tag
This should help CI avoid running the integration test logic in a
container where it's not currently possible.
2023-12-22 16:33:27 -08:00
Bruce MacDonald
db356c8519
post-response templating (#1427) 2023-12-22 17:07:05 -05:00
Daniel Hiltgen
96fb441abd
Merge pull request #1146 from dhiltgen/ext_server_cgo
Add cgo implementation for llama.cpp
2023-12-22 08:16:31 -08:00
Michael Yang
63aac0edc5 fix(test): use real version string for comparison 2023-12-19 15:03:02 -08:00
Daniel Hiltgen
51082535e1 Add automated test for multimodal
A simple test case that verifies llava:7b can read text in an image
2023-12-19 09:05:46 -08:00
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
5e7fd6906f Update images.go 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
3948c6ea06
add magic header for unit tests (#1558) 2023-12-18 10:41:02 -08:00
Patrick Devine
86b0dd4b16
add API create/copy handlers (#1541) 2023-12-15 11:59:18 -08:00
Patrick Devine
0174665d0e
add API tests for list handler (#1535) 2023-12-14 18:18:25 -08:00
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
Jeffrey Morgan
4a1abfe4fa fix tests 2023-12-13 14:42:30 -05:00
Patrick Devine
d9e60f634b
add image support to the chat api (#1490) 2023-12-12 13:28:58 -08:00
Jeffrey Morgan
0a9d348023
Fix issues with /set template and /set system (#1486) 2023-12-12 14:43:19 -05:00
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
Bruce MacDonald
3b0b8930d4
fix: only flush template in chat when current role encountered (#1426) 2023-12-08 16:44:24 -05:00
Bruce MacDonald
e3f925fc1b
fix: restore modelfile system in prompt template (#1425) 2023-12-08 14:20:19 -05:00
Michael Yang
1f05d77110
Merge pull request #1244 from jmorganca/brucemacd/no-fail-template
do not fail on unsupported template variables
2023-12-06 13:23:04 -08:00
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
Bruce MacDonald
47d4e22673 use missingkey in set empty interface when missing 2023-12-05 15:49:05 -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
409bb9674e
Merge pull request #1308 from jmorganca/mxyng/split-from
split from into one or more models
2023-12-05 14:33:03 -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
Michael Yang
998f1785b6 add modelfamilies 2023-12-04 16:59:23 -08:00
Michael Yang
70a93057cd refactor layer creation
previous layer creation was not ideal because:

1. it required reading the input file multiple times, once to calculate
   the sha256 checksum, another to write it to disk, and potentially one
   more to decode the underlying gguf
2. used io.ReadSeeker which is prone to user error. if the file isn't
   reset correctly or in the right place, it could end up reading an
   empty file

there are also some brittleness when reading existing layers else
writing the inherited layers will error reading an already closed file

this commit aims to fix these issues by restructuring layer creation.

1. it will now write the layer to a temporary file as well as the hash
   function and move it to the final location on Commit
2. layers are read once once when copied to the destination. exception
   is raw model files which still requires a second read to decode the
   model metadata
2023-12-04 16:59:23 -08:00
Michael Yang
2cb0fa7d40 split from into one or more models 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
Joshua Pham
bb80a597db Fix adapter loading from SHA hash 2023-12-01 13:50:55 -05:00
Michael Yang
13efd5f218 upload: fix PUT retry 2023-11-29 16:38:35 -08:00
Michael Yang
c4bdfffd96 upload: separate progress tracking 2023-11-29 16:38:33 -08:00
Michael Yang
26c63418e0 new hasher 2023-11-29 14:52:41 -08:00
Michael Yang
2799784ac8 revert checksum calculation to calculate-as-you-go 2023-11-29 13:47:58 -08:00
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
Patrick Devine
cde31cb220
Allow setting parameters in the REPL (#1294) 2023-11-29 09:56:42 -08:00
Bruce MacDonald
37d95157df
fix relative path on create (#1222) 2023-11-21 15:43:17 -05:00
Jeffrey Morgan
35c4b5ec16 calculate hash separately from http request 2023-11-20 15:45:11 -05:00
Jeffrey Morgan
9d73d3a6b5 add back part.Reset() 2023-11-19 14:32:19 -05:00
Jeffrey Morgan
72cd336410 dont retry on upload complete context cancel 2023-11-19 14:32:19 -05:00
Jeffrey Morgan
1bd594b2fa revert to using one open file for blob uploads 2023-11-19 14:32:19 -05:00
Jeffrey Morgan
9a8c21ac3d use exponential everywhere 2023-11-19 14:32:19 -05:00
Jeffrey Morgan
f6b317e8c9 fix sending too little data in chunk upload body 2023-11-19 14:32:19 -05:00
Jeffrey Morgan
ac5076ce1e exponential backoff up to 30s 2023-11-19 14:32:19 -05:00
Michael Yang
42c2e3a624 upload: retry complete upload 2023-11-19 14:32:19 -05:00
Michael Yang
cb42589792 adjust download/upload parts 2023-11-19 14:32:19 -05:00
Jeffrey Morgan
e1d7056496 update progress statuses 2023-11-19 09:21:13 -05:00
Jeffrey Morgan
02524a56ff check retry for authorization error 2023-11-19 00:19:53 -05:00
Jeffrey Morgan
12e046f12a remove unused function 2023-11-18 22:16:51 -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
c1bbf5ddee
Merge pull request #1134 from jmorganca/mxyng/progress
progress bar
2023-11-17 14:03:35 -08:00
Bruce MacDonald
0b19e24d81
only retry once on auth failure (#1175) 2023-11-17 14:22:35 -05:00