Commit Graph

699 Commits

Author SHA1 Message Date
Ettore Di Giacinto
25deb4ba95
chore(deps): update llama.cpp to 6262d13e0b2da91f230129a93a996609a2fa2f2 (#3549)
chore(deps): update llama.cpp to 6262d13e0b2da91f230129a93a996609a2f5a2f2

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-09-16 10:29:20 +02:00
LocalAI [bot]
3d3db1d74f
chore: ⬆️ Update ggerganov/whisper.cpp to 049b3a0e53c8a8e4c4576c06a1a4fccf0063a73f (#3548)
⬆️ Update ggerganov/whisper.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>
2024-09-15 21:40:51 +00:00
LocalAI [bot]
cabb1602e8
chore: ⬆️ Update ggerganov/llama.cpp to feff4aa8461da7c432d144c11da4802e41fef3cf (#3542)
⬆️ 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>
2024-09-13 22:05:38 +00:00
Ettore Di Giacinto
25e7661de2
chore(exllama): drop exllama backend (#3536)
* chore(exllama): drop exllama backend

For polishing and cleaning up it makes now sense to drop exllama which
is completely unmaintained, and was only supporting the llamav1
architecture (nowadays it's superseded by llamav1) .

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

* chore(gosec): fix CI

downgrade to latest known version of the gosec action

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-09-13 19:52:13 +00:00
Ettore Di Giacinto
d51444d606
chore(deps): update llama.cpp (#3497)
* Apply llava patch

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-09-12 20:55:27 +02:00
LocalAI [bot]
e35d8169b1
chore: ⬆️ Update ggerganov/whisper.cpp to a551933542d956ae84634937acd2942eb40efaaf (#3534)
⬆️ Update ggerganov/whisper.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>
2024-09-12 06:52:27 +00:00
LocalAI [bot]
5139dadceb
chore: ⬆️ Update ggerganov/whisper.cpp to 5caa19240d55bfd6ee316d50fbad32c6e9c39528 (#3494)
⬆️ Update ggerganov/whisper.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>
2024-09-08 00:00:38 +00:00
LocalAI [bot]
8b8522046d
chore: ⬆️ Update ggerganov/llama.cpp to 815b1fb20a53e439882171757825bacb1350de04 (#3489)
⬆️ 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>
2024-09-06 21:41:08 +00:00
LocalAI [bot]
58c4a6d9d9
chore: ⬆️ Update ggerganov/llama.cpp to 4db04784f96757d74f74c8c110c2a00d55e33514 (#3485)
⬆️ 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>
2024-09-05 22:08:12 +00:00
LocalAI [bot]
a9f438e1e6
chore: ⬆️ Update ggerganov/llama.cpp to 581c305186a0ff93f360346c57e21fe16e967bb7 (#3481)
⬆️ 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>
2024-09-05 06:15:46 +00:00
LocalAI [bot]
bf87943da7
chore: ⬆️ Update ggerganov/llama.cpp to 8962422b1c6f9b8b15f5aeaea42600bcc2d44177 (#3478)
⬆️ 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>
2024-09-03 21:42:11 +00:00
LocalAI [bot]
dbe1e652bc
chore: ⬆️ Update ggerganov/whisper.cpp to 5236f0278420ab776d1787c4330678d80219b4b6 (#3475)
⬆️ Update ggerganov/whisper.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>
2024-09-03 08:08:05 +00:00
LocalAI [bot]
e2d40d0fcc
chore: ⬆️ Update ggerganov/llama.cpp to 48baa61eccdca9205daf8d620ba28055c2347b64 (#3474)
⬆️ 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>
2024-09-03 03:48:23 +00:00
Ettore Di Giacinto
56db715a91
chore(deps): update whisper.cpp (#3443)
* chore(deps): update whisper.cpp

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

* chore: use clang

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

* fix: path for x86 is different

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

* test: try to skip whisper on mac x86_64

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-09-02 17:41:56 +02:00
Dave
c2804c42fe
fix: untangle pkg/grpc and core/schema for Transcription (#3419)
untangle pkg/grpc and core/schema in Transcribe

Signed-off-by: Dave Lee <dave@gray101.com>
2024-09-02 15:48:53 +02:00
LocalAI [bot]
3daba4731c
chore: ⬆️ Update ggerganov/llama.cpp to 8f1d81a0b6f50b9bad72db0b6fcd299ad9ecd48c (#3445)
⬆️ 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>
2024-09-01 21:41:56 +00:00
LocalAI [bot]
2259512345
chore: ⬆️ Update ggerganov/llama.cpp to a47667cff41f5a198eb791974e0afcc1cddd3229 (#3441)
⬆️ 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>
2024-08-31 21:40:57 +00:00
Ettore Di Giacinto
b8e7a76524
chore(deps): update llama.cpp (#3438)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-31 01:21:45 +02:00
LocalAI [bot]
ae6d327698
chore: ⬆️ Update ggerganov/llama.cpp to 9fe94ccac92693d4ae1bc283ff0574e8b3f4e765 (#3424)
⬆️ 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>
2024-08-29 07:56:31 +00:00
LocalAI [bot]
bc684c259c
chore: ⬆️ Update ggerganov/llama.cpp to 20f1789dfb4e535d64ba2f523c64929e7891f428 (#3417)
⬆️ 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>
2024-08-27 21:41:49 +00:00
LocalAI [bot]
6d0ede813f
chore: ⬆️ Update ggerganov/llama.cpp to 7d787ed96c32be18603c158ab0276992cf0dc346 (#3409)
⬆️ 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>
2024-08-27 08:44:08 +00:00
Ettore Di Giacinto
5d892f86ea
chore(cuda): reduce binary size (#3379)
fix(cuda): reduce binary size

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-26 14:47:36 +02:00
LocalAI [bot]
61fe2404a0
chore: ⬆️ Update ggerganov/llama.cpp to 3ba780e2a8f0ffe13f571b27f0bbf2ca5a199efc (#3361)
⬆️ 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>
2024-08-23 21:49:18 +00:00
LocalAI [bot]
7d030b56b2
chore: ⬆️ Update ggerganov/whisper.cpp to 9e3c5345cd46ea718209db53464e426c3fe7a25e (#3357)
⬆️ Update ggerganov/whisper.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>
2024-08-22 08:49:33 +00:00
LocalAI [bot]
0add16049e
chore: ⬆️ Update ggerganov/llama.cpp to fc54ef0d1c138133a01933296d50a36a1ab64735 (#3356)
⬆️ 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>
2024-08-21 22:14:02 +00:00
LocalAI [bot]
7cf59d9f98
chore: ⬆️ Update ggerganov/llama.cpp to 2f3c1466ff46a2413b0e363a5005c46538186ee6 (#3345)
⬆️ 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>
2024-08-21 00:37:13 +02:00
LocalAI [bot]
7147f1990f
chore: ⬆️ Update ggerganov/whisper.cpp to d65786ea540a5aef21f67cacfa6f134097727780 (#3344)
⬆️ Update ggerganov/whisper.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>
2024-08-20 22:20:34 +00:00
LocalAI [bot]
a495515e10
chore: ⬆️ Update ggerganov/llama.cpp to cfac111e2b3953cdb6b0126e67a2487687646971 (#3315)
⬆️ 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>
2024-08-20 12:16:39 +02:00
Ettore Di Giacinto
9475a6fa05
chore: drop petals (#3316)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-20 10:01:38 +02:00
LocalAI [bot]
3f74b34f06
chore: ⬆️ Update ggerganov/llama.cpp to 554b049068de24201d19dde2fa83e35389d4585d (#3263)
⬆️ 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>
2024-08-18 21:46:02 +00:00
LocalAI [bot]
5d416006ae
chore: ⬆️ Update ggerganov/llama.cpp to 2fb9267887d24a431892ce4dccc75c7095b0d54d (#3260)
⬆️ 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>
2024-08-17 21:46:26 +00:00
LocalAI [bot]
d6b3fbb4ad
chore: ⬆️ Update ggerganov/llama.cpp to 8b3befc0e2ed8fb18b903735831496b8b0c80949 (#3257)
⬆️ 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>
2024-08-16 21:50:54 +00:00
Ettore Di Giacinto
409e2d348e
chore(deps): bump llama.cpp, rename llama_add_bos_token (#3253)
deps(llama.cpp): bump, rename llama_add_bos_token

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-16 01:20:21 +02:00
LocalAI [bot]
121f143fc0
chore: ⬆️ Update ggerganov/llama.cpp to 5fd89a70ead34d1a17015ddecad05aaa2490ca46 (#3248)
⬆️ 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>
2024-08-14 21:44:38 +00:00
LocalAI [bot]
10324d9ad2
chore: ⬆️ Update ggerganov/llama.cpp to 06943a69f678fb32829ff06d9c18367b17d4b361 (#3245)
⬆️ 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>
2024-08-13 21:45:01 +00:00
LocalAI [bot]
89979da33f
chore: ⬆️ Update ggerganov/whisper.cpp to 22fcd5fd110ba1ff592b4e23013d870831756259 (#3239)
⬆️ Update ggerganov/whisper.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>
2024-08-13 02:01:26 +00:00
LocalAI [bot]
cd385c2720
chore: ⬆️ Update ggerganov/llama.cpp to fc4ca27b25464a11b3b86c9dbb5b6ed6065965c2 (#3240)
⬆️ 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>
2024-08-13 00:59:04 +00:00
LocalAI [bot]
e30114a4a4
chore: ⬆️ Update ggerganov/llama.cpp to 4134999e01f31256b15342b41c4de9e2477c4a6c (#3218)
⬆️ 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>
2024-08-11 21:46:30 +00:00
LocalAI [bot]
f3357a17b8
chore: ⬆️ Update ggerganov/llama.cpp to 6e02327e8b7837358e0406bf90a4632e18e27846 (#3212)
⬆️ 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>
2024-08-10 22:16:51 +00:00
LocalAI [bot]
a0e0804f25
chore: ⬆️ Update ggerganov/whisper.cpp to 81c999fe0a25c4ebbfef10ed8a1a96df9cfc10fd (#3209)
⬆️ Update ggerganov/whisper.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>
2024-08-09 22:35:22 +00:00
LocalAI [bot]
71b8232076
chore: ⬆️ Update ggerganov/llama.cpp to b72942fac998672a79a1ae3c03b340f7e629980b (#3208)
⬆️ 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>
2024-08-09 22:20:51 +00:00
Ettore Di Giacinto
9e3e892ac7
feat(p2p): add network explorer and community pools (#3125)
* WIP

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

* Fixups

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

* Wire up a simple explorer DB

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

* wip

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

* WIP

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

* refactor: group services id so can be identified easily in the ledger table

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

* feat(discovery): discovery service now gather worker informations correctly

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

* feat(explorer): display network token

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

* feat(explorer): display form to add new networks

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

* feat(explorer): stop from overwriting networks

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

* feat(explorer): display only networks with active workers

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

* feat(explorer): list only clusters in a network if it has online workers

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

* remove invalid and inactive networks

if networks have no workers delete them from the database, similarly,
if invalid.

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

* ci: add workflow to deploy new explorer versions automatically

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

* build-api: build with p2p tag

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

* Allow to specify a connection timeout

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

* logging

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

* Better p2p defaults

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

* Set loglevel

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

* Fix dht enable

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

* Default to info for loglevel

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

* Add navbar

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

* Slightly improve rendering

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

* Allow to copy the token easily

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>
2024-08-09 20:12:01 +02:00
LocalAI [bot]
74f8785047
chore: ⬆️ Update ggerganov/llama.cpp to 3a14e00366399040a139c67dd5951177a8cb5695 (#3204)
⬆️ 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>
2024-08-08 22:36:08 +00:00
LocalAI [bot]
b1773e33d5
chore: ⬆️ Update ggerganov/whisper.cpp to 6eac06759b87b50132a01be019e9250a3ffc8969 (#3203)
⬆️ Update ggerganov/whisper.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>
2024-08-08 22:18:00 +00:00
Ettore Di Giacinto
60117ec057
fix(apple): disable BUILD_TYPE metal on fallback (#3199)
When compiling the single-binary on Apple, we enforce BUILD_TYPE=metal,
however, we want still to have the fallback vanilla such as if llama.cpp fails
to load metal (e.g. if Acceleration framework is missing, or MacOS version is too old)
we can still run by offloading to the CPU. The default backend is still using metal as usual.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-08-08 00:59:10 -04:00
LocalAI [bot]
1c708d21de
chore: ⬆️ Update ggerganov/llama.cpp to 15fa07a5c564d3ed7e7eb64b73272cedb27e73ec (#3197)
⬆️ 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>
2024-08-07 22:19:20 +00:00
Ettore Di Giacinto
8814b31805
chore: drop gpt4all.cpp (#3106)
chore: drop gpt4all

gpt4all is already supported in llama.cpp - the backend was kept for
keeping compatibility with old gpt4all models (prior to gguf format).

It is good time now to clean up and remove it to slim the compilation
process.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-07 23:35:55 +02:00
Ettore Di Giacinto
abcf0ff000
chore: ⬆️ Update ggerganov/llama.cpp to 1e6f6554aa11fa10160a5fda689e736c3c34169f (#3189)
* arrow_up: Update ggerganov/llama.cpp

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

* fix(llama.cpp): adapt to upstream naming changes

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>
2024-08-07 01:10:21 +02:00
Ettore Di Giacinto
4e11ca55fd
chore: ⬆️ Update ggerganov/llama.cpp (#3166)
* arrow_up: Update ggerganov/llama.cpp

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

* fix(llama.cpp): adapt init function call

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>
2024-08-06 11:39:35 +02:00
LocalAI [bot]
1494ba13e6
chore: ⬆️ Update ggerganov/whisper.cpp (#3164)
⬆️ Update ggerganov/whisper.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>
2024-08-06 06:59:03 +00:00