Commit Graph

1957 Commits

Author SHA1 Message Date
Dave
d38e9090df
experiment: -j4 for build-linux: (#2514)
experiment: set -j4 to see if things go faster, while we wait for a proper fix from mudler

Signed-off-by: Dave Lee <dave@gray101.com>
2024-06-07 11:22:28 +02:00
Ettore Di Giacinto
b049805c9b
ci: run release build on self-hosted runners (#2505) 2024-06-06 22:16:34 -04:00
LocalAI [bot]
0f9b58f2cf
⬆️ Update ggerganov/llama.cpp (#2508)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-06 23:48:17 +00:00
LocalAI [bot]
0f134d557e
⬆️ Update ggerganov/whisper.cpp (#2507)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-06 23:21:25 +00:00
Ettore Di Giacinto
2676e127ae
models(gallery): add llama3-8b-feifei-1.0-iq-imatrix (#2511)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-07 00:17:59 +02:00
Ettore Di Giacinto
270d4f8413
models(gallery): add rawr_llama3_8b-iq-imatrix (#2510)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-07 00:12:11 +02:00
Ettore Di Giacinto
2d79cee8cb
models(gallery): add llama3-8B-aifeifei-1.0-iq-imatrix (#2509)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-07 00:07:20 +02:00
Ettore Di Giacinto
4c9623f50d
deps(whisper): update, add libcufft-dev (#2501)
* arrow_up: Update ggerganov/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* fix(build): add libcufft-dev

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

---------

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-06 08:41:04 +02:00
Ettore Di Giacinto
596cf76135
build(intel): bundle intel variants in single-binary (#2494)
* wip: try to build also intel variants

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

* Add dependencies

* Select automatically intel backend

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-06 08:40:51 +02:00
LocalAI [bot]
a293aa1b79
⬆️ Update ggerganov/llama.cpp (#2493)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-06 00:02:51 +00:00
Ettore Di Giacinto
c4eb02c80f
models(gallery): add l3-8b-stheno-v3.2-iq-imatrix (#2500)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-05 23:46:59 +02:00
Ettore Di Giacinto
9c9198ff08
models(gallery): add Llama-3-Yggdrasil-2.0-8B (#2499)
models(gallery): add Llama-3-Yggdrasil-2.0-8B-GGUF

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-05 23:42:23 +02:00
Ettore Di Giacinto
83c79d5453
models(gallery): add llama-3-instruct-8b-SimPO-ExPO (#2498)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-05 23:37:59 +02:00
Ettore Di Giacinto
88fd000065
models(gallery): add phi-3-4x4b (#2497)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-05 23:29:15 +02:00
Ettore Di Giacinto
956d652314
models(gallery): add nyun (#2496)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-05 23:22:58 +02:00
Ettore Di Giacinto
9ce2b4d71f
models(gallery): add dolphin-2.9.2-phi-3-Medium-abliterated (#2495)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-05 23:14:43 +02:00
Ettore Di Giacinto
4e974cb4fc
models(gallery): add dolphin-2.9.2-Phi-3-Medium (#2492)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-05 19:17:20 +02:00
Dave
d072835796
feat:OpaqueErrors to hide error information (#2486)
* adds a new configuration option to hide all error message information from http requests
---------

Signed-off-by: Dave Lee <dave@gray101.com>
2024-06-05 08:45:24 +02:00
Ettore Di Giacinto
17cf6c4a4d
feat(amdgpu): try to build in single binary (#2485)
* feat(amdgpu): try to build in single binary

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

* Release space from worker

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-05 08:44:15 +02:00
LocalAI [bot]
fab3e711ff
⬆️ Update ggerganov/llama.cpp (#2487)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-04 23:11:28 +00:00
Dave
4e1463fec2
feat: fiber CSRF (#2482)
new config option - enables or disables the fiber csrf middleware

Signed-off-by: Dave Lee <dave@gray101.com>
2024-06-04 19:43:46 +00:00
Dave
2fc6fe806b
fix: pkg/downloader should respect basePath for file:// urls (#2481)
* pass basePath down to pkg/downloader

Signed-off-by: Dave Lee <dave@gray101.com>

* enforce

Signed-off-by: Dave Lee <dave@gray101.com>

---------

Signed-off-by: Dave Lee <dave@gray101.com>
2024-06-04 14:32:47 +00:00
Ettore Di Giacinto
bdd6769b2d
feat(default): use number of physical cores as default (#2483)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-04 15:23:29 +02:00
Ettore Di Giacinto
1ffee9989f
README: update sponsors list (#2476)
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-06-04 15:23:00 +02:00
Dave
34ab442ce9
toil: bump grpc version (#2480)
bump the grpc package version

---------

Signed-off-by: Dave Lee <dave@gray101.com>
2024-06-04 08:39:19 +02:00
LocalAI [bot]
67aa31faad
⬆️ Update ggerganov/llama.cpp (#2477)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-03 23:09:24 +00:00
fakezeta
6ef78ef7f6
bugfix: CUDA acceleration not working (#2475)
* bugfix: CUDA acceleration not working

CUDA not working after #2286.
Refactored the code to be more polish

* Update requirements.txt

Missing imports

Signed-off-by: fakezeta <fakezeta@gmail.com>

* Update requirements.txt

Signed-off-by: fakezeta <fakezeta@gmail.com>

---------

Signed-off-by: fakezeta <fakezeta@gmail.com>
2024-06-03 22:41:42 +02:00
Ettore Di Giacinto
daa7544d9c
Update README.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-06-03 19:55:01 +02:00
Ettore Di Giacinto
34527737bb
feat(webui): enhance card visibility (#2473)
Do not let the description text to clutter, also highlight the model
names

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-03 17:07:26 +02:00
Ettore Di Giacinto
148adebe16
docs: fix p2p commands (#2472)
Also change icons on GPT vision page

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-03 16:58:53 +02:00
Ettore Di Giacinto
bae2a649fd
models(gallery): add new poppy porpoise versions (#2471)
models(gallery): add new poppy purpoise versions

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-03 15:44:52 +02:00
Ettore Di Giacinto
90945ebab3
models(gallery): add fimbulvetr iqmatrix version (#2470)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-03 15:44:27 +02:00
fakezeta
4a239a4bff
feat(transformers): various enhancements to the transformers backend (#2468)
update transformers

*Handle Temperature = 0 as greedy search
*Handle custom works as stop words
*Implement KV cache
*Phi 3 no more requires trust_remote_code: true
2024-06-03 08:52:55 +02:00
LocalAI [bot]
5ddaa19914
⬆️ Update ggerganov/llama.cpp (#2467)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-02 21:34:29 +00:00
Ettore Di Giacinto
77d752a481
fix(gemma): correctly format the template
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-06-02 10:51:58 +02:00
Ettore Di Giacinto
29ff51c12a
Update gemma stopwords
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-06-02 01:26:41 +02:00
Ettore Di Giacinto
c0744899c9
models(gallery): add gemma-2b (#2466)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-02 01:15:06 +02:00
LocalAI [bot]
c9092ad39c
models(gallery): ⬆️ update checksum (#2463)
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-01 23:13:02 +00:00
LocalAI [bot]
b588cae70e
⬆️ Update ggerganov/llama.cpp (#2465)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-01 22:31:32 +00:00
LocalAI [bot]
fb0f188c93
feat(swagger): update swagger (#2464)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-01 22:04:01 +00:00
Chakib Benziane
b99182c8d4
TTS API improvements (#2308)
* update doc on COQUI_LANGUAGE env variable

Signed-off-by: blob42 <contact@blob42.xyz>

* return errors from tts gRPC backend

Signed-off-by: blob42 <contact@blob42.xyz>

* handle speaker_id and language in coqui TTS backend

Signed-off-by: blob42 <contact@blob42.xyz>

* TTS endpoint: add optional language paramter

Signed-off-by: blob42 <contact@blob42.xyz>

* tts fix: empty language string breaks non-multilingual models

Signed-off-by: blob42 <contact@blob42.xyz>

* allow tts param definition in config file

- consolidate TTS options under `tts` config entry

Signed-off-by: blob42 <contact@blob42.xyz>

* tts: update doc

Signed-off-by: blob42 <contact@blob42.xyz>

---------

Signed-off-by: blob42 <contact@blob42.xyz>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-06-01 18:26:27 +00:00
Ettore Di Giacinto
95c65d67f5
models(gallery): add all whisper variants (#2462)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-01 20:04:03 +02:00
Ettore Di Giacinto
c603b95ac7
ci: pin build-time protoc (#2461)
ci: pin protoc

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-01 18:59:15 +02:00
Ettore Di Giacinto
13cfa6de0a
models(gallery): add Neural SOVLish Devil (#2460)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-01 12:54:58 +02:00
Ettore Di Giacinto
0560c6fd57
models(gallery): add poppy porpoise 1.0 (#2459)
modekls(gallery): add poppy porpoise 1.0

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-01 12:54:37 +02:00
Ettore Di Giacinto
f24dddae42
models(gallery): add ultron (#2456)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-01 00:09:51 +02:00
LocalAI [bot]
06b461b061
⬆️ Update ggerganov/llama.cpp (#2453)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-01 00:09:26 +02:00
Ettore Di Giacinto
e50a7ba879
models(gallery): add llama3-11b (#2455)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-01 00:03:57 +02:00
Ettore Di Giacinto
3b2bce1fc9
models(gallery): add anjir (#2454)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-01 00:03:46 +02:00
LocalAI [bot]
3fe7e9f678
⬆️ Update ggerganov/whisper.cpp (#2452)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-31 21:59:48 +00:00