mirror/LocalAI
1
0 Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-09-27 00:24:58 -04:00
Code Issues Packages Projects Releases Wiki Activity
8,130 Commits 228 Branches 178 Tags
feat/system-model-vram-11970
Commit Graph
807 Commits
Author SHA1 Message Date
localai-org-maint-botandmudler d270c2823c chore: ⬆️ Update PrismML-Eng/llama.cpp to adfffbe41b2cabcd51fff326ab045662265062bb (#12271) 
⬆️ Update PrismML-Eng/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>
 2026-09-26 09:01:43 +02:00
localai-org-maint-botandmudler 8f29d5d271 chore: ⬆️ Update ikawrakow/ik_llama.cpp to 1aaf7105be6e55a97fa4a9fd6f5bd362b08436dc (#12270) 
⬆️ Update ikawrakow/ik_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>
 2026-09-26 09:01:32 +02:00
localai-org-maint-botandmudler ded329854c chore: ⬆️ Update 0xShug0/audio.cpp to e79205f3e0083d04e812e1a4a376f71be97e9a22 (#12269) 
⬆️ Update 0xShug0/audio.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>
 2026-09-26 09:01:15 +02:00
localai-org-maint-botandmudler c511b6dadf chore: ⬆️ Update ggml-org/llama.cpp to 84e76d8a23162eca70490da131945ebec1f09bf4 (#12258) 
⬆️ Update ggml-org/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>
 2026-09-25 14:59:38 +02:00
localai-org-maint-botandmudler 1768dac662 chore: ⬆️ Update PrismML-Eng/llama.cpp to 842b1880415d6f508f03b789e5ce70194def7bfd (#12250) 
⬆️ Update PrismML-Eng/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>
 2026-09-25 09:29:04 +02:00
localai-org-maint-botandmudler c678654d3e chore: ⬆️ Update 0xShug0/audio.cpp to 857de2366ed74bdb2c37f85259089e3a0a6b8cb0 (#12248) 
⬆️ Update 0xShug0/audio.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>
 2026-09-25 09:07:58 +02:00
localai-org-maint-botandmudler 1b961c0aca chore: ⬆️ Update ikawrakow/ik_llama.cpp to 20f7a72edd7049fe5a87eef2b5e9a50ae109ca4b (#12251) 
⬆️ Update ikawrakow/ik_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>
 2026-09-25 09:07:50 +02:00
localai-org-maint-botandmudler 11b3b184ea chore: ⬆️ Update PrismML-Eng/llama.cpp to 0324c66521960d67aa7da8687fb1453a79a6565c (#12226) 
⬆️ Update PrismML-Eng/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>
 2026-09-24 21:19:15 +02:00
localai-org-maint-botandmudler fdd19c7f76 chore: ⬆️ Update ggml-org/llama.cpp to d2e54583c7452353eb35d40431281f6ee984332f (#12228) 
⬆️ Update ggml-org/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>
 2026-09-24 21:18:47 +02:00
localai-org-maint-botandmudler df45e6cab8 chore: ⬆️ Update 0xShug0/audio.cpp to 9bdd1d908bbd128e9eb405f5a8e38d0defb84c72 (#12224) 
⬆️ Update 0xShug0/audio.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>
 2026-09-24 17:05:19 +02:00
localai-org-maint-botandmudler 91b462db24 chore: ⬆️ Update ikawrakow/ik_llama.cpp to f3d6e6e3020ddfebad60113845bf521620766da5 (#12233) 
⬆️ Update ikawrakow/ik_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>
 2026-09-24 09:05:08 +02:00
mudler-agentandEttore Di Giacinto 81eaca8768 fix(turboquant): extend D512 flash-attn patch to all turbo V types (#12234) 
The previous patch only removed DECL_FATTN_VEC_CASE_D512 for turbo2_0
and turbo3_0 V cache types. turbo4_0 also overflows shared memory
(0x10100 bytes > 0xc000 max), causing ptxas errors on CUDA 12/13.

Additionally, the previous patch was incomplete: it only removed the
template instantiations but not the dispatch calls in fattn.cu or the
extern declarations in fattn-vec.cuh. This caused linker errors
(undefined reference to ggml_cuda_flash_attn_ext_vec_case_d512).

This patch removes all three layers for all turbo V types:
- Template instance .cu files (DECL_FATTN_VEC_CASE_D512)
- Dispatch calls in fattn.cu (FATTN_VEC_CASE_D512)
- Extern declarations in fattn-vec.cuh (extern DECL_FATTN_VEC_CASE_D512)

Signed-off-by: mudler <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
 2026-09-24 08:01:28 +02:00
localai-org-maint-botmudlerEttore Di Giacinto
 		2ccda5ba92 chore: ⬆️ Update TheTom/llama-cpp-turboquant to 4deec5587b2963af00bdf80884f3337e02eb7d64 (#12154) 
* ⬆️ Update TheTom/llama-cpp-turboquant

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

* fix(turboquant): patch D512 flash-attn shared memory overflow

turboquant 4deec55 added DECL_FATTN_VEC_CASE_D512 for TURBO2_0 and
TURBO3_0 V cache types. The D=512 kernel template with these types
allocates 65 KB of shared memory, exceeding the 48 KB GPU limit:

  ptxas error: Entry function uses too much shared data
  (0x10100 bytes, 0xc000 max)

Carry the fix as a patch under backend/cpp/turboquant/patches/ until
TheTom/llama-cpp-turboquant#386 is merged upstream.

TURBO4_0 (4-bit) does not overflow and is left unchanged.

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>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
 2026-09-23 21:12:38 +00:00
Plamen K. Kosseff e7306a087a feat(audio-cpp): AUDIOCPP_DEFAULT_BACKEND fallback for models without a backend option (#12133) 
Models whose options carry no explicit backend: open their session on the
CPU backend even in accelerator images. The gallery entries carry
backend:best since #11892; this covers hand-written model configurations
the same way, per deployment: the environment variable supplies the
fallback, an explicit backend: option always wins (merged beside the
existing threads and maingpu fallbacks), and validation reuses the
option parser.

Assisted-by: Claude:claude-fable-5

Signed-off-by: Plamen K. Kosseff <p.kosseff@gmail.com>
 2026-09-23 12:16:31 +02:00
localai-org-maint-botandmudler 01c60b22e6 chore: ⬆️ Update 0xShug0/audio.cpp to 1ee4ce8275997a7dcf0e2a5dc3410e509b898d6d (#12211) 
⬆️ Update 0xShug0/audio.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>
 2026-09-23 11:04:08 +02:00
localai-org-maint-botandmudler 90e6cae60e chore: ⬆️ Update PrismML-Eng/llama.cpp to bdc23b56b4458b9f1655aec5287f3ab56ee8daaa (#12207) 
⬆️ Update PrismML-Eng/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>
 2026-09-23 09:28:12 +02:00
localai-org-maint-botandmudler 82f7b25766 chore: ⬆️ Update ikawrakow/ik_llama.cpp to c5b5773bed338c5f3b985d277764a4d780b83d42 (#12210) 
⬆️ Update ikawrakow/ik_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>
 2026-09-23 09:26:14 +02:00
localai-org-maint-botandmudler 74b5cf1311 chore: ⬆️ Update ggml-org/llama.cpp to 709fe755dfa810d77e2ac386292b29648b536864 (#12208) 
⬆️ Update ggml-org/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>
 2026-09-23 09:26:01 +02:00
localai-org-maint-botandmudler 2d55aafb86 chore: ⬆️ Update ggml-org/llama.cpp to 58367713a6935c0810103378144008df32e3d5db (#12197) 
⬆️ Update ggml-org/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>
 2026-09-22 12:57:00 +02:00
localai-org-maint-botandmudler 937d19545d chore: ⬆️ Update ikawrakow/ik_llama.cpp to baac291dc9d531927760b48451d8dfcb63b6adec (#12192) 
⬆️ Update ikawrakow/ik_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>
 2026-09-22 09:08:03 +02:00
localai-org-maint-botandmudler c7820cd4df chore: ⬆️ Update PrismML-Eng/llama.cpp to 01ae597e3f7d4742909e1e831abb12fe3d24b2cf (#12195) 
⬆️ Update PrismML-Eng/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>
 2026-09-22 09:07:50 +02:00
localai-org-maint-botandmudler 1a04ca3fbf chore: ⬆️ Update 0xShug0/audio.cpp to 17cc8980e9c8f8073796aead8a91c809511cbab1 (#12199) 
⬆️ Update 0xShug0/audio.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>
 2026-09-22 09:07:05 +02:00
localai-org-maint-botandmudler 728e08c6c2 chore: ⬆️ Update ggml-org/llama.cpp to ce8caa6e60a03093351d6016a818720e0d46f0fb (#12177) 
⬆️ Update ggml-org/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>
 2026-09-21 15:46:22 +02:00
localai-org-maint-botandmudler 08158a5c4d chore: ⬆️ Update 0xShug0/audio.cpp to e3de8e3f3cbfac55ffa58df71426c41550a8598b (#12176) 
⬆️ Update 0xShug0/audio.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>
 2026-09-21 10:11:15 +02:00
localai-org-maint-botandmudler 276d376575 chore: ⬆️ Update ikawrakow/ik_llama.cpp to 9cba2e3874df6f598fd339c4c6c7d5fc2b44645b (#12174) 
⬆️ Update ikawrakow/ik_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>
 2026-09-21 09:05:25 +02:00
localai-org-maint-botandmudler 515590998a chore: ⬆️ Update antirez/ds4 to 0aaea5a238fb41a35106a551e73c8409dfb751ac (#12168) 
⬆️ Update antirez/ds4

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-21 08:26:08 +02:00
localai-org-maint-botandmudler 19a66fd898 chore: ⬆️ Update ggml-org/llama.cpp to e613ef2c81bae98d59850d061ac29e6e3e88cb00 (#12157) 
⬆️ Update ggml-org/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>
 2026-09-20 22:00:45 +02:00
localai-org-maint-botandmudler 416847e20d chore: ⬆️ Update PrismML-Eng/llama.cpp to 9a9394a895b96003ca842a6041cb28ac49a108f7 (#12114) 
⬆️ Update PrismML-Eng/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>
 2026-09-20 12:35:49 +02:00
localai-org-maint-botandmudler 1678129e91 chore: ⬆️ Update 0xShug0/audio.cpp to a7b58a6d3d6ae4143c485266b1c6c09898ad8c72 (#12150) 
⬆️ Update 0xShug0/audio.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>
 2026-09-20 12:32:09 +02:00
localai-org-maint-botandmudler 8ef96e692e chore: ⬆️ Update ikawrakow/ik_llama.cpp to 401a09d2f534d2eeabb0a37919ebc5a2cbc56ac6 (#12151) 
⬆️ Update ikawrakow/ik_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>
 2026-09-20 12:31:35 +02:00
localai-org-maint-botandmudler 8b01583e70 chore: ⬆️ Update 0xShug0/audio.cpp to a074d6b8cdb16b89cd028876e83629a538d49b9a (#12125) 
⬆️ Update 0xShug0/audio.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>
 2026-09-19 09:29:01 +02:00
localai-org-maint-botandmudler e7d295e5f1 chore: ⬆️ Update ggml-org/llama.cpp to 50631b3d2c569ad8e5c112090cd28570b1268ee0 (#12129) 
⬆️ Update ggml-org/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>
 2026-09-19 09:28:28 +02:00
localai-org-maint-botandmudler 99682b768e chore: ⬆️ Update ikawrakow/ik_llama.cpp to 2ae132fa601ea06818ed3584f50f7eb4f72d4967 (#12131) 
⬆️ Update ikawrakow/ik_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>
 2026-09-19 09:28:06 +02:00
localai-org-maint-botandmudler e73c67f592 chore: ⬆️ Update 0xShug0/audio.cpp to f2b4937306daa25f5c78520f3c626ed31495a37a (#12086) 
⬆️ Update 0xShug0/audio.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>
 2026-09-18 09:00:08 +02:00
localai-org-maint-botandmudler a5565badf1 chore: ⬆️ Update ikawrakow/ik_llama.cpp to dc31024448b8f18eac0cd5c2e200b6c7e015ef7a (#12088) 
⬆️ Update ikawrakow/ik_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>
 2026-09-18 08:57:43 +02:00
localai-org-maint-botandmudler 11e0b70c3c chore: ⬆️ Update ggml-org/llama.cpp to 972d2313bc0bf0a45f634f77d95c9fb03aeab12c (#12090) 
⬆️ Update ggml-org/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>
 2026-09-18 08:52:34 +02:00
localai-org-maint-botandmudler 1be130880c chore: ⬆️ Update antirez/ds4 to 8db1d1d155cb0400a86a86b9c62d0defb3a6148b (#12093) 
⬆️ Update antirez/ds4

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-17 08:10:41 +02:00
localai-org-maint-botandmudler 43e89ae552 chore: ⬆️ Update PrismML-Eng/llama.cpp to 7dffb158de30ebb8ef9d64f33c6b0b2d7c1e6313 (#12072) 
⬆️ Update PrismML-Eng/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>
 2026-09-16 19:39:48 +02:00
localai-org-maint-botandmudler 456a77e155 chore: ⬆️ Update ggml-org/llama.cpp to 38a5b42d9a3e82e0a586bcd1caed121f36c87a73 (#12075) 
⬆️ Update ggml-org/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>
 2026-09-16 19:39:32 +02:00
localai-org-maint-botandmudler bca37c1678 chore: ⬆️ Update 0xShug0/audio.cpp to 4af143229384fb6da3f373dc87de145ae954609b (#12073) 
⬆️ Update 0xShug0/audio.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>
 2026-09-16 08:55:32 +02:00
localai-org-maint-botandmudler e7a382a7a3 chore: ⬆️ Update ikawrakow/ik_llama.cpp to d85a1d7e91e5bc2f83a796542a8d5c436d32c99f (#12078) 
⬆️ Update ikawrakow/ik_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>
 2026-09-16 08:27:20 +02:00
localai-org-maint-botandmudler 790c53fa27 chore: ⬆️ Update ggml-org/llama.cpp to 96ffdc41ceb055e1c2d3d96667ae6d9f0ccb710b (#12057) 
⬆️ Update ggml-org/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>
 2026-09-15 09:01:50 +02:00
localai-org-maint-botandmudler 287e425c64 chore: ⬆️ Update PrismML-Eng/llama.cpp to 6ac5eb087009a762a3f61876f7dc152bc8600bf4 (#12055) 
⬆️ Update PrismML-Eng/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>
 2026-09-15 09:01:39 +02:00
localai-org-maint-botandmudler d1ad8a600f chore: ⬆️ Update antirez/ds4 to 9139e2ae58a41503968a500f36f75895c1ba63fc (#12062) 
⬆️ Update antirez/ds4

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-09-15 01:05:54 +02:00
localai-org-maint-botandmudler 97660b19b9 chore: ⬆️ Update 0xShug0/audio.cpp to 582a63ca8b6f76235f1b8636e734930218c78c05 (#12056) 
⬆️ Update 0xShug0/audio.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>
 2026-09-15 00:57:55 +02:00
localai-org-maint-botandmudler b64b210999 chore: ⬆️ Update ikawrakow/ik_llama.cpp to 7434a014237e55b2e0d36edc2ace6acfb82fea1c (#12052) 
⬆️ Update ikawrakow/ik_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>
 2026-09-15 00:57:28 +02:00
localai-org-maint-botmudlerEttore Di Giacinto
 		f9dab888fe chore: ⬆️ Update TheTom/llama-cpp-turboquant to 407f3237bfb3eeaff61546797de3d8c1a96be748 (#12003) 
* ⬆️ Update TheTom/llama-cpp-turboquant

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

* fix(turboquant): follow renamed RPC server target

The pinned TurboQuant fork now exposes the RPC server as
ggml-rpc-server. Build that target and copy its renamed artifact while
preserving LocalAI's packaged turboquant-rpc-server name.

Assisted-by: Codex:gpt-5
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>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
 2026-09-14 14:07:29 +00:00
localai-org-maint-botmudlerEttore Di Giacinto
 		9c157b88bb chore: ⬆️ Update PrismML-Eng/llama.cpp to d8f26eec76da6d09bb708bcba51ef64b8cd868a3 (#12005) 
* ⬆️ Update PrismML-Eng/llama.cpp

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

* fix(bonsai): follow updated fork APIs

The updated PrismML fork implements common_json_error directly, so preserve the shared gRPC source instead of rewriting it to the removed nlohmann exception type. Build and copy the renamed ggml-rpc-server target as well.

Assisted-by: Codex:gpt-5

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>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
 2026-09-14 13:40:14 +00:00
localai-org-maint-botmudlerEttore Di Giacinto
 		6ca6a073e9 chore: ⬆️ Update ggml-org/llama.cpp to 5f436dddb440a288ee5611d7d1eca564a6aca9f4 (#12008) 
* ⬆️ Update ggml-org/llama.cpp

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

* fix(llama-cpp): disable PCH for SYCL builds

IntelLLVM cannot bundle the precompiled headers introduced by the latest
llama.cpp update. Disable PCH for both SYCL variants while retaining it
for the other backends.

Assisted-by: Codex:gpt-5
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>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
 2026-09-14 13:27:38 +00:00
localai-org-maint-botmudlerEttore Di Giacinto
 		c50b46996c chore: ⬆️ Update antirez/ds4 to a04f46fa423e45712c8c7e430eff422479f314a3 (#12013) 
* ⬆️ Update antirez/ds4

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

* fix(ds4): link engram support in GPU builds

The bumped ds4 engine moved DeepSeek v4.1 engram helpers into a new object. Build and link that object for CUDA and Metal while retaining the upstream CPU object set.

Assisted-by: Codex:gpt-5
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>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
 2026-09-14 15:24:31 +02:00