Commit graph

3531 commits

Author SHA1 Message Date
LocalAI [bot]
2ac4a86bb4
chore: ⬆️ Update ggerganov/llama.cpp to 8a8c4ceb6050bd9392609114ca56ae6d26f5b8f5 (#4825)
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2025-02-13 21:49:57 +00:00
Ettore Di Giacinto
8670d480a6
chore(model gallery): add nvidia_aceinstruct-72b (#4822)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-13 09:58:34 +01:00
Ettore Di Giacinto
af0b4ff237
chore(ci): update labels
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2025-02-13 09:58:19 +01:00
Ettore Di Giacinto
e694764065
chore(model gallery): add nvidia_aceinstruct-7b (#4821)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-13 09:44:53 +01:00
Ettore Di Giacinto
f3c27e0381
chore(model gallery): add nvidia_aceinstruct-1.5b (#4819)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-13 09:33:40 +01:00
LocalAI [bot]
bf44319d0d
chore: ⬆️ Update ggerganov/llama.cpp to 0fb77f821f6e70ad8b8247a97d1022f0fef78991 (#4814)
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2025-02-12 22:41:53 +00:00
Ettore Di Giacinto
5b133a640b
chore(model gallery): add theskullery_l3.3-exp-unnamed-model-70b-v0.5 (#4813)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-12 11:05:51 +01:00
Ettore Di Giacinto
0030a3fe75
chore(model gallery): add simplescaling_s1.1-32b (#4812)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-12 11:03:05 +01:00
Ettore Di Giacinto
0a748b009e chore(ci): avoit cache hits until the ci gRPC job is fixed
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-12 09:11:40 +01:00
LocalAI [bot]
257e951def
chore: ⬆️ Update ggerganov/llama.cpp to 90e4dba461b07e635fd1daf3b491c978c7dd0013 (#4810)
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2025-02-12 00:13:28 +01:00
LocalAI [bot]
fbd82a2dd0
feat(swagger): update swagger (#4809)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2025-02-11 21:54:40 +00:00
Ettore Di Giacinto
5db321dad2 chore(ci): do not always regenerate the cache
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-11 16:36:00 +01:00
Ettore Di Giacinto
f5638a6354
feat(diffusers): allow to override image gen options (#4807)
Use the options field in the model to override kwargs if needed.

This allows to specify from the model yaml config:

```yaml

options:
- foo:bar

```

And each option will be used directly when calling the diffusers
pipeline, e.g:

```python
pipe(
  foo="bar",
)
```

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-11 10:16:32 +01:00
Ettore Di Giacinto
5f64cc6328
Revert "chore(deps): Bump docs/themes/lotusdocs from f5785a2 to 975da91" (#4808)
Revert "chore(deps): Bump docs/themes/lotusdocs from `f5785a2` to `975da91` (…"

This reverts commit e57b750ca3.
2025-02-11 10:05:57 +01:00
Ettore Di Giacinto
28b10e8804
chore(swagger): update (#4805)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-11 09:51:01 +01:00
Ettore Di Giacinto
3277f5095d
chore(model gallery): add agentica-org_deepscaler-1.5b-preview (#4804)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-11 09:47:19 +01:00
Ettore Di Giacinto
fe3ced2919 chore(ci): try again to bump parallelism in grpc jobs
As we moved these out to self-hosted

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-11 09:31:00 +01:00
LocalAI [bot]
45e37a07bb
chore: ⬆️ Update ggerganov/llama.cpp to 19b392d58dc08c366d0b29bd3b9c6991fa4e1662 (#4803)
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2025-02-11 09:17:02 +01:00
dependabot[bot]
e57b750ca3
chore(deps): Bump docs/themes/lotusdocs from f5785a2 to 975da91 (#4801)
Bumps [docs/themes/lotusdocs](https://github.com/colinwilson/lotusdocs) from `f5785a2` to `975da91`.
- [Release notes](https://github.com/colinwilson/lotusdocs/releases)
- [Commits](f5785a2399...975da91e83)

---
updated-dependencies:
- dependency-name: docs/themes/lotusdocs
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-02-10 22:27:14 +00:00
Ettore Di Giacinto
49df492268 chore(ci): run grpc build on self-hosted
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-10 19:44:50 +01:00
Ettore Di Giacinto
516cd660f1
chore(grpcio): reduce parallelism (#4799)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-10 18:56:13 +01:00
Ettore Di Giacinto
8fd3ace9a1
chore(grpcio): bump to 1.70 (#4798)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-10 18:38:53 +01:00
Ettore Di Giacinto
099469cb05
chore(tests): decrease parallelism for gRPC builds (#4797)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-10 12:59:59 +01:00
Ettore Di Giacinto
6be8c0c618
chore(model gallery): add localai-functioncall-qwen2.5-7b-v0.5 (#4796)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-10 12:07:35 +01:00
Dave
3cddf24747
feat: Centralized Request Processing middleware (#3847)
* squash past, centralize request middleware PR

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

* migrate bruno request files to examples repo

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

* fix

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

* Update tests/e2e-aio/e2e_test.go

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

---------

Signed-off-by: Dave Lee <dave@gray101.com>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2025-02-10 12:06:16 +01:00
Ettore Di Giacinto
c330360785
chore(model gallery): add ilsp_llama-krikri-8b-instruct (#4795)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-10 09:54:54 +01:00
LocalAI [bot]
8cd51570e5
chore: ⬆️ Update ggerganov/llama.cpp to 19d3c8293b1f61acbe2dab1d49a17950fd788a4a (#4793)
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2025-02-09 22:12:01 +00:00
Ettore Di Giacinto
0e7aa5cd15
chore(model gallery): add subtleone_qwen2.5-32b-erudite-writer (#4792)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-09 10:59:46 +01:00
Ettore Di Giacinto
e06a5f49de
chore(model gallery): add huihui-ai_deepseek-r1-distill-llama-70b-abliterated (#4790)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-09 10:53:48 +01:00
Dave
fb2f847507
chore: migrate bruno request files to examples repo (#4788)
migrate bruno request files to examples repo

Signed-off-by: Dave Lee <dave@gray101.com>
2025-02-09 10:52:28 +01:00
LocalAI [bot]
e01acc88c9
chore: ⬆️ Update ggerganov/llama.cpp to e6e658319952f7ad269dc11275b9edddc721fc6d (#4787)
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2025-02-08 21:57:40 +00:00
LocalAI [bot]
7a5912908a
chore: ⬆️ Update ggerganov/llama.cpp to d2fe216fb2fb7ca8627618c9ea3a2e7886325780 (#4780)
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2025-02-08 09:44:34 +01:00
Ettore Di Giacinto
4b1b942a7f
chore(model gallery): add sicariussicariistuff_redemption_wind_24b (#4781)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-08 09:04:18 +01:00
Ettore Di Giacinto
230fe0098f
chore(model gallery): add cognitivecomputations_dolphin3.0-mistral-24b (#4779)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-07 13:33:24 +01:00
Ettore Di Giacinto
cc163429dc
chore(model gallery): add cognitivecomputations_dolphin3.0-r1-mistral-24b (#4778)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-07 13:31:49 +01:00
Ettore Di Giacinto
f670e0a91c
chore(model gallery): add nohobby_l3.3-prikol-70b-v0.5 (#4777)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-07 13:29:53 +01:00
LocalAI [bot]
731674eee7
chore: ⬆️ Update ggerganov/llama.cpp to 8a59053f63fffc24e730cd3ea067760abfe4a919 (#4776)
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2025-02-06 22:02:00 +00:00
Ettore Di Giacinto
cc1f6f913f
fix(llama.cpp): disable mirostat as default (#2911)
Even if increasing the quality of the output, it has shown to have
performance drawbacks to be so noticeable that the confuses users about
speed of LocalAI ( see also
https://github.com/mudler/LocalAI/issues/2780 ).

This changeset disables Mirostat by default (which can
be still enabled manually).

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Dave <dave@gray101.com>
2025-02-06 19:39:59 +01:00
Ettore Di Giacinto
7f90ff7aec
chore(llama-ggml): drop deprecated backend (#4775)
The GGML format is now dead, since in the next version of LocalAI we
already bring many breaking compatibility changes, taking the occasion
also to drop ggml support (pre-gguf).

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-06 18:36:23 +01:00
Ettore Di Giacinto
8d45670e41
fix(openai): consistently return stop reason (#4771)
We were not returning a stop reason when no tool was actually called
(even if specified).

Fixes: https://github.com/mudler/LocalAI/issues/4716

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-06 12:41:08 +01:00
Ettore Di Giacinto
e4b8ddb6a1
chore(model gallery): add black-ink-guild_pernicious_prophecy_70b (#4774)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-06 12:03:59 +01:00
Ettore Di Giacinto
a801561f81
chore(model gallery): add tiger-lab_qwen2.5-32b-instruct-cft (#4773)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-06 12:01:56 +01:00
Ettore Di Giacinto
16ced07102
chore(model gallery): add arliai_llama-3.3-70b-arliai-rpmax-v1.4 (#4772)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-06 11:59:14 +01:00
LocalAI [bot]
d35595372d
chore: ⬆️ Update ggerganov/llama.cpp to d774ab3acc4fee41fbed6dbfc192b57d5f79f34b (#4770)
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2025-02-06 09:02:51 +01:00
LocalAI [bot]
81be192279
chore: ⬆️ Update leejet/stable-diffusion.cpp to d46ed5e184b97c2018dc2e8105925bdb8775e02c (#4769)
⬆️ Update leejet/stable-diffusion.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2025-02-05 23:49:15 +00:00
Ettore Di Giacinto
28a1310890 chore(docs): enhance visibility
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-05 19:50:32 +01:00
Ettore Di Giacinto
2a702e9ca4 chore(docs): small updates
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-05 19:49:11 +01:00
Ettore Di Giacinto
3ecaea1b6e chore(docs): update sponsors in the website
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-05 19:41:55 +01:00
Ettore Di Giacinto
7daf5ac3e3
fix(gallery): do not return overrides and additional config (#4768)
When hitting /models/available we are intersted in the model
description, name and small metadatas. Configuration and overrides are
part of internals which are required only for installation.

This also solves a current bug when hitting /models/available fails if
one of the gallery items have overrides with parameters defined

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-05 18:37:09 +01:00
Ettore Di Giacinto
7bc80c17f8
chore(model gallery): add LocalAI-functioncall-llama3.2-3b-v0.5 (#4766)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-02-05 10:19:31 +01:00