mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-04-30 03:55:58 -04:00
Code Issues Packages Projects Releases Wiki Activity
6,174 Commits 94 Branches 143 Tags
f4036fa83f748c8aa48ca055134ac11f5b5eeb37
Commit Graph

289 Commits

Author SHA1 Message Date
LocalAI [bot]
05e94bd9e7 chore: ⬆️ Update ggml-org/llama.cpp to f53577432541bb9edc1588c4ef45c66bf07e4468 (#9577) 
⬆️ 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>
 2026-04-27 08:57:24 +02:00
LocalAI [bot]
d9cb0d6133 chore: ⬆️ Update ggml-org/llama.cpp to dcad77cc3b0865153f486327064fb0320a57a476 (#9572) 
⬆️ 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>
 2026-04-26 12:38:35 +02:00
LocalAI [bot]
47cc3dc8d7 chore: ⬆️ Update ggml-org/llama.cpp to 361fe72acb7b9bd79059cc177cbeda99b35b5db9 (#9548) 
⬆️ 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>
 2026-04-25 08:58:27 +02:00
LocalAI [bot]
7c1934b183 chore: ⬆️ Update ggml-org/llama.cpp to 187a45637054881ecacf17f8e2f6f8f2ba7df1c7 (#9520) 
⬆️ 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>
 2026-04-24 09:17:06 +02:00
Ettore Di Giacinto
ed648b3b4e fix(llama-cpp): include server-chat.cpp in grpc-server translation unit (#9511) 
* fix(llama-cpp): include server-chat.cpp in grpc-server translation unit

Upstream llama.cpp refactor (ggml-org/llama.cpp#20690) moved the
OAI/Anthropic/Responses and transcription conversion helpers out of
server-common.cpp into a new server-chat.cpp, and server-task.cpp and
server-context.cpp now call those symbols (convert_transcriptions_to_chatcmpl,
server_chat_convert_responses_to_chatcmpl, server_chat_convert_anthropic_to_oai,
server_chat_msg_diff_to_json_oaicompat) via server-chat.h.

grpc-server.cpp builds as a single translation unit by #include-ing the
upstream .cpp files directly. Without including server-chat.cpp, the
declarations are satisfied at compile time via server-chat.h but the
link step fails with undefined references once LLAMA_VERSION crosses
the refactor commit (134d6e54).

Guard the include with __has_include so the same source stays buildable
on older LLAMA_VERSION pins that predate the refactor (where prepare.sh
won't copy server-chat.cpp into tools/grpc-server/).

Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(llama-cpp): bump LLAMA_VERSION to 0d0764dfd

Bump to ggml-org/llama.cpp@0d0764dfd2.
Paired with the preceding grpc-server server-chat.cpp include so the
refactor at 134d6e54 links cleanly. Supersedes PR #9494.

Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-04-23 14:59:39 +02:00
LocalAI [bot]
cd7b035716 chore: ⬆️ Update ggml-org/llama.cpp to 5a4cd6741fc33227cdacb329f355ab21f8481de2 (#9479) 
⬆️ 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>
 2026-04-22 08:58:19 +02:00
LocalAI [bot]
8bb1e8f21f chore: ⬆️ Update ggml-org/llama.cpp to cf8b0dbda9ac0eac30ee33f87bc6702ead1c4664 (#9448) 
⬆️ 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>
 2026-04-21 11:15:45 +02:00
LocalAI [bot]
babbbc6ec8 chore: ⬆️ Update ggml-org/llama.cpp to 4eac5b45095a4e8a1ff1cce4f6d030e0872fb4ad (#9429) 
⬆️ 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>
 2026-04-19 23:39:19 +02:00
LocalAI [bot]
6e49dba27c chore: ⬆️ Update ggml-org/llama.cpp to 4f02d4733934179386cbc15b3454be26237940bb (#9415) 
⬆️ 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>
 2026-04-19 09:26:05 +02:00
Keith Mattix II
8839a71c87 fix(rocm): add gfx1151 support and expose AMDGPU_TARGETS build-arg (#9410) 
Add gfx1151 (AMD Strix Halo / Ryzen AI MAX) to the default AMDGPU_TARGETS
list in the llama-cpp backend Makefile. ROCm 7.2.1 ships with gfx1151
Tensile libraries, so this architecture should be included in default builds.

Also expose AMDGPU_TARGETS as an ARG/ENV in Dockerfile.llama-cpp so that
users building for non-default GPU architectures can override the target
list via --build-arg AMDGPU_TARGETS=<arch>. Previously, passing
-DAMDGPU_TARGETS=<arch> through CMAKE_ARGS was silently overridden by
the Makefile's own append of the default target list.

Fixes #9374

Signed-off-by: Keith Mattix <keithmattix2@gmail.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-04-18 20:39:40 +02:00
Ettore Di Giacinto
c49feb546f fix(llama-cpp): rename linked target common -> llama-common (#9408) 
Upstream llama.cpp (45cac7ca) renamed the CMake library target
`common` to `llama-common`. Linking the old name caused
`target_include_directories(... PUBLIC .)` from the common/ dir
to not propagate, so `#include "common.h"` failed when building
grpc-server.
 2026-04-18 00:42:05 +02:00
LocalAI [bot]
7dbd9c056a chore: ⬆️ Update ggml-org/llama.cpp to 4fbdabdc61c04d1262b581e1b8c0c3b119f688ff (#9381) 
⬆️ 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>
 2026-04-17 08:13:04 +02:00
Ettore Di Giacinto
5837b14888 chore: ⬆️ Update TheTom/llama-cpp-turboquant to `45f8a066ed5f5bb38c695cec532f6cef9f4efa9d' (#9385) 
chore: ⬆️ Update TheTom/llama-cpp-turboquant to `45f8a066ed5f5bb38c695cec532f6cef9f4efa9d`

Drop 0002-ggml-rpc-bump-op-count-to-97.patch; the fork now has
GGML_OP_COUNT == 97 and RPC_PROTO_PATCH_VERSION 2 upstream.

Fetch all tags in backend/cpp/llama-cpp/Makefile so tag-only commits
(the new turboquant pin is reachable only through the tag
feature-turboquant-kv-cache-b8821-45f8a06) can be checked out.
 2026-04-17 08:12:21 +02:00
LocalAI [bot]
96cd561d9d chore: ⬆️ Update ggml-org/llama.cpp to b3d758750a268bf93f084ccfa3060fb9a203192a (#9370) 
⬆️ 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>
 2026-04-16 01:12:39 +02:00
LocalAI [bot]
62862ca06b chore: ⬆️ Update ggml-org/llama.cpp to fae3a28070fe4026f87bd6a544aba1b2d1896566 (#9357) 
⬆️ 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>
 2026-04-15 01:25:41 +02:00
Ettore Di Giacinto
87e6de1989 feat: wire transcription for llama.cpp, add streaming support (#9353) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-04-14 16:13:40 +02:00
LocalAI [bot]
906acba8db chore: ⬆️ Update ggml-org/llama.cpp to e97492369888f5311e4d1f3beb325a36bbed70e9 (#9347) 
⬆️ 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>
 2026-04-14 08:54:25 +02:00
LocalAI [bot]
ea32b8953f chore: ⬆️ Update ggml-org/llama.cpp to 1e9d771e2c2f1113a5ebdd0dc15bafe57dce64be (#9330) 
⬆️ 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>
 2026-04-13 09:42:18 +02:00
Ettore Di Giacinto
151ad271f2 feat(rocm): bump to 7.x (#9323) 
feat(rocm): bump to 7.2.1

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-04-12 08:51:30 +02:00
LocalAI [bot]
6fbda277c5 chore: ⬆️ Update ggml-org/llama.cpp to ff5ef8278615a2462b79b50abdf3cc95cfb31c6f (#9319) 
⬆️ 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>
 2026-04-11 23:15:23 +02:00
LocalAI [bot]
62a674ce12 chore: ⬆️ Update ggml-org/llama.cpp to e62fa13c2497b2cd1958cb496e9489e86bbd5182 (#9312) 
⬆️ 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>
 2026-04-11 08:39:10 +02:00
LocalAI [bot]
d4cd6c284f chore: ⬆️ Update ggml-org/llama.cpp to d132f22fc92f36848f7ccf2fc9987cd0b0120825 (#9302) 
⬆️ 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>
 2026-04-10 08:46:45 +02:00
Ettore Di Giacinto
2b05420f95 chore(llama.cpp): bump to 'd12cc3d1ca6bba741cd77887ac9c9ee18c8415c7' (#9282) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-04-09 08:12:05 +02:00
LocalAI [bot]
0526e60f8d chore: ⬆️ Update ggml-org/llama.cpp to 66c4f9ded01b29d9120255be1ed8d5835bcbb51d (#9269) 
⬆️ 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>
 2026-04-08 08:27:38 +02:00
LocalAI [bot]
bccaba1f66 chore: ⬆️ Update ggml-org/llama.cpp to d0a6dfeb28a09831d904fc4d910ddb740da82834 (#9259) 
⬆️ 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>
 2026-04-07 00:38:36 +02:00
LocalAI [bot]
0dda4fe6f0 chore: ⬆️ Update ggml-org/llama.cpp to 761797ffdf2ce3f118e82c663b1ad7d935fbd656 (#9243) 
⬆️ 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>
 2026-04-06 10:52:38 +02:00
Ettore Di Giacinto
c5a840f6af fix(reasoning): warm-up 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-04-04 20:25:24 +00:00
LocalAI [bot]
7962dd16f7 chore: ⬆️ Update ggml-org/llama.cpp to d006858316d4650bb4da0c6923294ccd741caefd (#9215) 
⬆️ 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>
 2026-04-04 09:44:39 +02:00
LocalAI [bot]
c0a023d13d chore: ⬆️ Update ggml-org/llama.cpp to a1cfb645307edc61a89e41557f290f441043d3c2 (#9203) 
⬆️ 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>
 2026-04-03 08:30:15 +02:00
LocalAI [bot]
26f1b94f4d chore: ⬆️ Update ggml-org/llama.cpp to 95a6ebabb277c4cc18247e7bc2a5502133caca63 (#9199) 
⬆️ 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>
 2026-04-02 08:53:16 +02:00
LocalAI [bot]
cc5f33ce95 chore: ⬆️ Update ggml-org/llama.cpp to 0fcb3760b2b9a3a496ef14621a7e4dad7a8df90f (#9196) 
⬆️ 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>
 2026-04-01 00:48:40 +02:00
LocalAI [bot]
b0b37a472f chore: ⬆️ Update ggml-org/llama.cpp to 08f21453aec846867b39878500d725a05bd32683 (#9190) 
⬆️ 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>
 2026-03-31 09:27:08 +02:00
LocalAI [bot]
3d738164b7 chore: ⬆️ Update ggml-org/llama.cpp to 7c203670f8d746382247ed369fea7fbf10df8ae0 (#9160) 
⬆️ 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>
 2026-03-30 08:27:26 +02:00
LocalAI [bot]
4c870288d9 chore: ⬆️ Update ggml-org/llama.cpp to 59d840209a5195c2f6e2e81b5f8339a0637b59d9 (#9144) 
⬆️ 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>
 2026-03-28 18:18:06 +01:00
LocalAI [bot]
b86fa63f70 chore: ⬆️ Update ggml-org/llama.cpp to a970515bdb0b1d09519106847660b0d0c84d2472 (#9137) 
⬆️ 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>
 2026-03-26 07:56:41 +01:00
LocalAI [bot]
9bc68b2721 chore: ⬆️ Update ggml-org/llama.cpp to 9f102a1407ed5d73b8c954f32edab50f8dfa3f58 (#9127) 
⬆️ 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>
 2026-03-25 07:52:14 +01:00
LocalAI [bot]
2ad8c149e0 chore: ⬆️ Update ggml-org/llama.cpp to 1772701f99dd3fc13f5783b282c2361eda8ca47c (#9123) 
⬆️ 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>
 2026-03-24 00:35:40 +01:00
LocalAI [bot]
31fcb1425d chore: ⬆️ Update ggml-org/llama.cpp to 49bfddeca18e62fa3d39114a23e9fcbdf8a22388 (#9102) 
⬆️ 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>
 2026-03-23 01:11:18 +01:00
LocalAI [bot]
b74111feed chore: ⬆️ Update ggml-org/llama.cpp to 990e4d96980d0b016a2b07049cc9031642fb9903 (#9095) 
⬆️ 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>
 2026-03-22 00:57:39 +01:00
LocalAI [bot]
aa3e82976e chore: ⬆️ Update ggml-org/llama.cpp to 4cb7e0bd61e7e1101e8ab10db5dee70c5717a386 (#9087) 
⬆️ 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>
 2026-03-21 09:41:11 +01:00
Ettore Di Giacinto
c3174f9543 chore(deps): bump llama-cpp to 'a0bbcdd9b6b83eeeda6f1216088f42c33d464e38' (#9079) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-03-20 08:12:21 +01:00
LocalAI [bot]
9a9da062e1 chore: ⬆️ Update ggml-org/llama.cpp to 5744d7ec430e2f875a393770195fda530560773f (#9063) 
⬆️ 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>
 2026-03-19 07:58:30 +01:00
LocalAI [bot]
a58475dbef chore: ⬆️ Update ggml-org/llama.cpp to ee4801e5a6ee7ee4063144ab44ab4e127f76fba8 (#9044) 
⬆️ 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>
 2026-03-18 08:46:12 +01:00
LocalAI [bot]
118bcee196 chore: ⬆️ Update ggml-org/llama.cpp to 9b342d0a9f2f4892daec065491583ec2be129685 (#9039) 
⬆️ 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>
 2026-03-17 10:22:42 +01:00
LocalAI [bot]
b2030255ca chore: ⬆️ Update ggml-org/llama.cpp to 88915cb55c14769738fcab7f1c6eaa6dcc9c2b0c (#9020) 
⬆️ 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>
 2026-03-16 00:10:11 +01:00
LocalAI [bot]
87525109f1 chore: ⬆️ Update ggml-org/llama.cpp to 3a6f059909ed5dab8587df5df4120315053d57a4 (#9009) 
⬆️ 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>
 2026-03-15 09:46:45 +01:00
LocalAI [bot]
977063c4ba chore: ⬆️ Update ggml-org/llama.cpp to e30f1fdf74ea9238ff562901aa974c75aab6619b (#8997) 
⬆️ 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>
 2026-03-14 01:16:42 +01:00
LocalAI [bot]
46a8941a2c chore: ⬆️ Update ggml-org/llama.cpp to 57819b8d4b39d893408e51520dff3d47d1ebb757 (#8983) 
⬆️ 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>
 2026-03-13 07:59:15 +01:00
LocalAI [bot]
270eb956c7 chore: ⬆️ Update ggml-org/llama.cpp to 10e5b148b061569aaee8ae0cf72a703129df0eab (#8946) 
⬆️ 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>
 2026-03-11 08:04:09 +01:00
LocalAI [bot]
b48920ecf6 chore: ⬆️ Update ggml-org/llama.cpp to 23fbfcb1ad6c6f76b230e8895254de785000be46 (#8921) 
⬆️ 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>
 2026-03-10 07:30:43 +01:00