Commit Graph

246 Commits

Author SHA1 Message Date
Ettore Di Giacinto
c62504ac92
cleanup: drop bloomz and ggllm as now supported by llama.cpp (#1217)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-10-26 07:43:31 +02:00
Ettore Di Giacinto
f227e918f9
feat(llama.cpp): Bump llama.cpp, adapt grpc server (#1211)
* feat(llama.cpp): Bump llama.cpp, adapt grpc server

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* ci: fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-10-25 20:56:25 +02:00
LocalAI [bot]
9196583651
⬆️ Update ggerganov/llama.cpp (#1204)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-10-23 19:06:39 +02:00
LocalAI [bot]
c377e61ff0
⬆️ Update go-skynet/go-llama.cpp (#1156)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-10-22 08:55:44 +02:00
Ettore Di Giacinto
1a7be035d3 fix(Makefile): build all backends if none is specified
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-10-21 11:34:59 +02:00
Ettore Di Giacinto
004baaa30f feat(llama.cpp): update
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-10-21 11:04:03 +02:00
Ettore Di Giacinto
432513c3ba
ci: add GPU tests (#1095)
* ci: test GPU

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* ci: show logs

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Debug

* debug

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* split extra/core images

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* split extra/core images

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* consider runner host dir

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-10-19 13:50:40 +02:00
Ettore Di Giacinto
128694213f
feat: llama.cpp gRPC C++ backend (#1170)
* wip: llama.cpp c++ gRPC server

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* make it work, attach it to the build process

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* update deps

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: add protobuf dep

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* try fix protobuf on cmake

* cmake: workarounds

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* add packages

* cmake: use fixed version of grpc

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* cmake(grpc): install locally

* install grpc

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* install required deps for grpc on debian bullseye

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* debug

* debug

* Fixups

* no need to install cmake manually

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* ci: fixup macOS

* use brew whenever possible

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* macOS fixups

* debug

* fix container build

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* workaround

* try mac

https://stackoverflow.com/questions/23905661/on-mac-g-clang-fails-to-search-usr-local-include-and-usr-local-lib-by-def

* Disable temp. arm64 docker image builds

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-10-16 21:46:29 +02:00
LocalAI [bot]
07249c0446
⬆️ Update go-skynet/go-llama.cpp (#1136)
Bump of go-skynet/go-llama.cpp version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-10-05 17:35:21 +02:00
LocalAI [bot]
e660721a0c
⬆️ Update go-skynet/go-llama.cpp (#1130)
Bump of go-skynet/go-llama.cpp version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-10-04 16:54:20 +02:00
LocalAI [bot]
46660a16a0
⬆️ Update go-skynet/go-llama.cpp (#1106)
Bump of go-skynet/go-llama.cpp version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-09-29 23:55:12 +00:00
65a
55e38fea0e
feat(llama.cpp): enable ROCm/HIPBLAS support (#1100)
**Description**

This PR fixes lack of HIPBLAS support in LocalAI.

**Notes for Reviewers**
This PR builds on https://github.com/go-skynet/go-llama.cpp/pull/235 to
enable ROCm/HIPBLAS support for gguf models running under llama.cpp
backend (not the stable ggml one). It can be enabled by using
BUILD_TYPE=hipblas. This was tested on a gfx1100 card, but should work
for gfx900,gfx1030 and other cards. Card support can be set with
AMDGPU_TARGETS environment variable.

**[Signed
commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)**
- [x] Yes, I signed my commits.
 
<!--
Thank you for contributing to LocalAI! 

Contributing Conventions
-------------------------

The draft above helps to give a quick overview of your PR.

Remember to remove this comment and to at least:

1. Include descriptive PR titles with [<component-name>] prepended. We
use [conventional
commits](https://www.conventionalcommits.org/en/v1.0.0/).
2. Build and test your changes before submitting a PR (`make build`). 
3. Sign your commits
4. **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below).
5. **X/Twitter handle:** we announce bigger features on X/Twitter. If
your PR gets announced, and you'd like a mention, we'll gladly shout you
out!

By following the community's contribution conventions upfront, the
review process will
be accelerated and your PR merged more quickly.

If no one reviews your PR within a few days, please @-mention @mudler.
-->

---------

Signed-off-by: 65a <65a@63bit.net>
2023-09-28 21:42:20 +02:00
Ettore Di Giacinto
601e54000d
fix(llama.cpp): update, run go mod tidy (#1088)
**Description**

This PR supersedes #1086

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-09-22 00:45:02 +02:00
ci-robbot [bot]
7bdf707dd3
⬆️ Update go-skynet/go-llama.cpp (#1084)
Bump of go-skynet/go-llama.cpp version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-09-20 19:48:38 +02:00
ci-robbot [bot]
a8fb4d23f8
⬆️ Update go-skynet/go-llama.cpp (#1062)
Bump of go-skynet/go-llama.cpp version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-09-17 08:38:28 +02:00
ci-robbot [bot]
8590f5a599
⬆️ Update go-skynet/go-llama.cpp (#1048)
Bump of go-skynet/go-llama.cpp version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-09-14 10:40:36 +02:00
ci-robbot [bot]
0b28220f2b
⬆️ Update go-skynet/go-llama.cpp (#1043)
Bump of go-skynet/go-llama.cpp version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-09-13 09:16:33 +02:00
ci-robbot [bot]
255c31bddf
⬆️ Update go-skynet/go-llama.cpp (#1027)
Bump of go-skynet/go-llama.cpp version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-09-11 09:42:54 +02:00
Ettore Di Giacinto
c0bb5c4bf6 feat(vllm): Initial vllm backend implementation
Related to: https://github.com/go-skynet/LocalAI/issues/1015

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-09-09 17:03:23 +02:00
Ettore Di Giacinto
cc74fc93b4
feat(llama.cpp): update (#1024)
**Description**

This PR fixes #

**Notes for Reviewers**


**[Signed
commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)**
- [ ] Yes, I signed my commits.
 

<!--
Thank you for contributing to LocalAI! 

Contributing Conventions:

1. Include descriptive PR titles with [<component-name>] prepended.
2. Build and test your changes before submitting a PR. 
3. Sign your commits

By following the community's contribution conventions upfront, the
review process will
be accelerated and your PR merged more quickly.
-->

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-09-08 18:38:22 +02:00
Ettore Di Giacinto
dc307a1cc0
feat: add vall-e-x (#1007)
**Description**

This PR fixes #985 

**Notes for Reviewers**


**[Signed
commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)**
- [ ] Yes, I signed my commits.
 

<!--
Thank you for contributing to LocalAI! 

Contributing Conventions:

1. Include descriptive PR titles with [<component-name>] prepended.
2. Build and test your changes before submitting a PR. 
3. Sign your commits

By following the community's contribution conventions upfront, the
review process will
be accelerated and your PR merged more quickly.
-->

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-09-04 19:25:23 +02:00
ci-robbot [bot]
b3eb5c860b
⬆️ Update go-skynet/go-llama.cpp (#1005)
Bump of go-skynet/go-llama.cpp version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-09-04 19:11:41 +02:00
Bo-Yi Wu
1c2f7409e3
chore(deps): remove unused package (#1003)
**Description**

Just remove Golang unused package and update the format in Makefile

Signed-off-by: appleboy <appleboy.tw@gmail.com>
2023-09-04 19:11:28 +02:00
ci-robbot [bot]
0e7e8eec53
⬆️ Update go-skynet/go-llama.cpp (#1002)
Bump of go-skynet/go-llama.cpp version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-09-03 10:00:01 +02:00
ci-robbot [bot]
c332499252
⬆️ Update go-skynet/go-llama.cpp (#996)
Bump of go-skynet/go-llama.cpp version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-09-02 09:54:50 +02:00
Ettore Di Giacinto
1ff30034e8
fix(deps): update go-llama.cpp (#980)
**Description**

This PR bumps llama.cpp (adding support to gguf v2) and changes the
default test model

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-08-30 23:01:55 +02:00
ci-robbot [bot]
cc84dfd50f
⬆️ Update go-skynet/go-llama.cpp (#968)
Bump of go-skynet/go-llama.cpp version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-08-28 08:23:51 +02:00
Ettore Di Giacinto
44bc7aa3d0
feat: Allow to load lora adapters for llama.cpp (#955)
**Description**

This PR fixes #

**Notes for Reviewers**


**[Signed
commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)**
- [ ] Yes, I signed my commits.
 

<!--
Thank you for contributing to LocalAI! 

Contributing Conventions:

1. Include descriptive PR titles with [<component-name>] prepended.
2. Build and test your changes before submitting a PR. 
3. Sign your commits

By following the community's contribution conventions upfront, the
review process will
be accelerated and your PR merged more quickly.
-->

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-08-25 21:58:46 +02:00
ci-robbot [bot]
7f0c88ed3e
⬆️ Update go-skynet/go-llama.cpp (#954)
Bump of go-skynet/go-llama.cpp version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-08-25 18:45:40 +02:00
ci-robbot [bot]
d15508f52c
⬆️ Update nomic-ai/gpt4all (#953)
Bump of nomic-ai/gpt4all version

Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-08-25 01:19:48 +02:00
Ettore Di Giacinto
1120847f72
feat: bump llama.cpp, add gguf support (#943)
**Description**

This PR syncs up the `llama` backend to use `gguf`
(https://github.com/go-skynet/go-llama.cpp/pull/180). It also adds
`llama-stable` to the targets so we can still load ggml. It adapts the
current tests to use the `llama-backend` for ggml and uses a `gguf`
model to run tests on the new backend.

In order to consume the new version of go-llama.cpp, it also bump go to
1.21 (images, pipelines, etc)

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-08-24 01:18:58 +02:00
Ettore Di Giacinto
ab5b75eb01
feat: add llama-stable backend (#932)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-08-20 16:35:42 +02:00
ci-robbot [bot]
dbb1f86455
⬆️ Update nomic-ai/gpt4all (#911)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-08-19 10:17:41 +02:00
Dave
8cb1061c11
Usage Features (#863) 2023-08-18 21:23:14 +02:00
ci-robbot [bot]
0c73a637f1
⬆️ Update nomic-ai/gpt4all (#899)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-08-16 01:11:54 +02:00
ci-robbot [bot]
63d91af555
⬆️ Update nomic-ai/gpt4all (#878)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-08-15 09:25:10 +02:00
Ettore Di Giacinto
77e1ae3d70
feat(Makefile): allow to restrict backend builds (#890)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-08-13 20:04:08 +02:00
Ettore Di Giacinto
c81e9d8d1f fix: add exllama to protogen 2023-08-11 01:02:31 +02:00
Ettore Di Giacinto
8c781a6a44
feat: Add Diffusers (#874)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-08-09 08:38:51 +02:00
ci-robbot [bot]
0e4f93c5cf
⬆️ Update nomic-ai/gpt4all (#870)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-08-08 21:57:01 +02:00
Ettore Di Giacinto
433605e282 feat: add initial Bark backend implementation
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-08-07 22:53:28 +02:00
Ettore Di Giacinto
a843e64fc2 feat: add initial AutoGPTQ backend implementation 2023-08-07 22:53:28 +02:00
ci-robbot [bot]
6b900e28cd
⬆️ Update nomic-ai/gpt4all (#859)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-08-03 19:07:53 +02:00
Ettore Di Giacinto
5ca21ee398
feat: add ngqa and RMSNormEps parameters (#860)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-08-03 00:51:08 +02:00
Ettore Di Giacinto
1e37ec727d
Revert "⬆️ Update go-skynet/go-llama.cpp" (#850) 2023-08-01 19:09:18 +02:00
ci-robbot [bot]
ae36bae59d
⬆️ Update nomic-ai/gpt4all (#847)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-08-01 00:48:10 +02:00
ci-robbot [bot]
a0324245f1
⬆️ Update nomic-ai/gpt4all (#841)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-31 19:14:56 +02:00
ci-robbot [bot]
18e1cb9c92
⬆️ Update nomic-ai/gpt4all (#825)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-30 09:48:30 +02:00
ci-robbot [bot]
e7ceb9e8f5
⬆️ Update go-skynet/go-llama.cpp (#824)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-30 09:48:10 +02:00
Ettore Di Giacinto
096d98c3d9
fix: add rope settings during model load, fix CUDA (#821)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-27 21:56:05 +02:00