3828 Commits

Author SHA1 Message Date
Michael Yang
b698f9a0d8
build: add missing dependencies (#8896) v0.5.8-rc9 2025-02-06 13:12:16 -08:00
Azis Alvriyanto
32285a6d19
format: rename test file from byte_test.go to bytes_test.go (#8865) 2025-02-06 13:06:15 -08:00
Michael Yang
1c198977ec
ci: fix linux archive (#8862)
the find returns intermediate directories which pulls the parent
directories. it also omits files under lib/ollama.

switch back to globbing
v0.5.8-rc8
2025-02-05 19:45:58 -08:00
zyphixor
330b6c50b0
readme: add simple-discord-ai to community integrations (#8659) 2025-02-05 18:35:04 -08:00
Diego Pereira
928911bc68
runner: avoid buffer overwrite when generating multiple embeddings (#8714)
Shield the code processing the embedding result
from subsequent calls that may overwrite the same
buffer to process a second input when retrieving
model embeddings.
2025-02-05 16:53:33 -08:00
Michael Yang
5b446cc815
chore: update gitattributes (#8860)
* chore: update gitattributes
* chore: add build info source
2025-02-05 16:37:18 -08:00
Daniel Lok
451c1596af
readme: add MLflow Tracing as an observability integration (#8811) 2025-02-05 16:04:24 -08:00
Michael Yang
932bded12f chore: add optional field for server logs 2025-02-05 15:55:32 -08:00
Michael Yang
070ad913ac ci: fix linux archive 2025-02-05 15:08:02 -08:00
Azis Alvriyanto
8d8b9f83ae
format: byte formatting test coverage (#8692)
Removed redundant checks and streamlined the switch-case structure.
Added test cases for both HumanBytes and HumanBytes2 to cover a wide range of scenarios.
2025-02-05 12:23:07 -08:00
Jeffrey Morgan
f00d359a67
docs: add section in development.md on library detection (#8855) 2025-02-05 11:16:27 -08:00
Yashwanth A
291def6adb
server: increase timeout in stall detection from 5s to 30s (#8831)
In some cases, downloads slow due to disk i/o or other factors,
causing the download to restart a part. This causes the download
to "reverse" in percent completion. By increasing the timeout to 30s,
this should happen less frequently.
v0.5.8-rc7
2025-02-05 10:00:26 -08:00
Jeffrey Morgan
cd3fbf1c49
llama: use dynamic backend loading for mllama and clip (#8835) 2025-02-05 09:46:56 -08:00
Jeffrey Morgan
c852b8e021
server: always print upload/download part info (#8832) 2025-02-04 19:30:49 -08:00
William
d8932c55e7
server: fix out of bounds exception on model download (#8746) 2025-02-04 18:52:47 -08:00
Michael Yang
63f0269f7f ci: split docker build by platform
this improves build reliability and concurrency
v0.5.8-rc6
2025-02-04 17:04:27 -08:00
Jeffrey Morgan
4759ecae19
ml/backend/ggml: fix library loading on macOS amd64 (#8827) 2025-02-04 15:05:39 -08:00
Michael Yang
65b7ecac7b fix extra quote v0.5.8-rc5 2025-02-04 08:35:30 -08:00
Michael Yang
f9d2d89135 fix linux archive v0.5.8-rc4 2025-02-03 16:12:33 -08:00
Michael Yang
669dc31cf3 fix build v0.5.8-rc3 2025-02-03 15:10:51 -08:00
Tilman Griesel
d4d338c224
readme: add Chipper to community integrations (#8803) 2025-02-03 14:18:19 -08:00
Melroy van den Berg
bfdeffc375
docs: use OLLAMA_VERSION=0.5.7 for install version override (#8802) 2025-02-03 13:54:08 -08:00
Michael Yang
e806184023 fix release workflow v0.5.8-rc2 2025-02-03 13:19:57 -08:00
Jeffrey Morgan
50566113ac
llm: do not error if LibOllamaPath does not exist (#8801) 2025-02-03 12:27:48 -08:00
Davide Bertoni
ad22ace439
docs: add missing json and shell code blocks in api.md (#8766) 2025-02-02 13:12:55 -08:00
Anıl Kaynar
f4321a421c
readme: add MinimalNextOllamaChat to community integrations (#8767) 2025-02-02 12:56:10 -08:00
Michael Yang
475333d533 fix docker build-args
env context is not accessible from job.*.strategy. since it's in the
environment, just tell docker to use the environment variable[1]

[1]: https://docs.docker.com/reference/cli/docker/buildx/build/#build-arg
v0.5.8-rc1
2025-01-31 14:56:02 -08:00
Michael Yang
39fd89308c build: set CFLAGS=-O3 specifically for cpu.go v0.5.8-rc0 2025-01-31 10:25:39 -08:00
Michael Yang
548a9f56a6 Revert "cgo: use O3"
This reverts commit bea1f1fac6b6b51bb3b8a666789c518b7aaa8b94.
2025-01-31 10:25:39 -08:00
Michael Yang
3f0cb36bdb build: set goflags in linux release 2025-01-30 13:07:32 -08:00
Michael Yang
bea1f1fac6 cgo: use O3 2025-01-30 12:21:50 -08:00
Jeffrey Morgan
5d75d837ef
discover: fix default LibOllamaPath value (#8702) 2025-01-30 12:21:38 -08:00
Parth Sareen
711648c9bb
docs: update api.md with streaming with tools is enabled (#8676) 2025-01-29 15:14:30 -08:00
Michael Yang
dcfb7a105c
next build (#8539)
* add build to .dockerignore

* test: only build one arch

* add build to .gitignore

* fix ccache path

* filter amdgpu targets

* only filter if autodetecting

* Don't clobber gpu list for default runner

This ensures the GPU specific environment variables are set properly

* explicitly set CXX compiler for HIP

* Update build_windows.ps1

This isn't complete, but is close.  Dependencies are missing, and it only builds the "default" preset.

* build: add ollama subdir

* add .git to .dockerignore

* docs: update development.md

* update build_darwin.sh

* remove unused scripts

* llm: add cwd and build/lib/ollama to library paths

* default DYLD_LIBRARY_PATH to LD_LIBRARY_PATH in runner on macOS

* add additional cmake output vars for msvc

* interim edits to make server detection logic work with dll directories like lib/ollama/cuda_v12

* remove unncessary filepath.Dir, cleanup

* add hardware-specific directory to path

* use absolute server path

* build: linux arm

* cmake install targets

* remove unused files

* ml: visit each library path once

* build: skip cpu variants on arm

* build: install cpu targets

* build: fix workflow

* shorter names

* fix rocblas install

* docs: clean up development.md

* consistent build dir removal in development.md

* silence -Wimplicit-function-declaration build warnings in ggml-cpu

* update readme

* update development readme

* llm: update library lookup logic now that there is one runner (#8587)

* tweak development.md

* update docs

* add windows cuda/rocm tests

---------

Co-authored-by: jmorganca <jmorganca@gmail.com>
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
2025-01-29 15:03:38 -08:00
Xiaofu Huang
2ef3c803a1
readme: add AI Toolkit for VSCode to community integrations (#8604) 2025-01-27 00:36:23 -08:00
Matěj Štágl
453e4d090b
readme: add LlmTornado to community integrations (#8551) 2025-01-25 01:04:07 -08:00
Daniel Jalkut
ca2f9843c8
docs: remove reference to the deleted examples folder (#8524) 2025-01-22 22:52:15 -08:00
frob
294b6f5a22
docs: remove tfs_z option from documentation (#8515) 2025-01-21 09:28:59 -08:00
EndoTheDev
7bb356c680
docs: update suspend header in gpu.md (#8487) 2025-01-19 18:45:35 -08:00
Jannik Maierhöfer
021817e59a
readme: add link to Langfuse (#8455) 2025-01-16 22:41:12 -08:00
Patrick Devine
a420a453b4
fix default modelfile for create (#8452) v0.5.7 2025-01-16 01:14:04 -08:00
Jeffrey Morgan
42cf4db601
parser: fix parsing Modelfiles with multiple FROM commands (#8449) 2025-01-16 00:14:04 -08:00
Josh
93a8daf285
convert: import support for command-r models from safetensors (#6063)
---------

Co-authored-by: Patrick Devine <patrick@infrahq.com>
2025-01-15 16:31:22 -08:00
Gloryjaw
a041b4df7c
docs: fix path to examples (#8438) 2025-01-15 11:49:12 -08:00
Patrick Devine
2539f2dbf9
Fix absolute path names + gguf detection (#8428) v0.5.6 2025-01-14 19:01:24 -08:00
Jeffrey Morgan
61676fb506
llama: move grammar tests to llama_test.go (#8411) 2025-01-14 12:55:45 -08:00
Bruce MacDonald
f6f3713001
convert: qwen2 from safetensors (#8408)
Add native support for converting Qwen2 family models (including Qwen2.5)
from safetensors to gguf format so we can run it.
2025-01-14 10:34:37 -08:00
Steve Berdy
a30f347201
readme: add LangChain for .NET to community integrations (#8352) 2025-01-14 09:37:35 -08:00
Jeffrey Morgan
74ea4fb604
remove .prettierrc.json (#8413) 2025-01-14 09:30:34 -08:00
Jeffrey Morgan
6982e9cc96
readme: remove link to missing page 2025-01-13 18:56:31 -08:00