vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
6937 commits 3 branches 196 tags 386 MiB
Commit graph

805 commits

Author SHA1 Message Date
Concedo
ed8b881c68 rc 1.83.1 2025-02-09 13:20:17 +08:00
Concedo
fc50a29426 Merge branch 'concedo_experimental' of https://github.com/LostRuins/koboldcpp into concedo_experimental 2025-02-09 13:17:29 +08:00
Concedo
1cb42bf260 support running in single process mode without admin flag 2025-02-09 13:17:14 +08:00
Roman Garanin
c0a16b5d4f
Sort model configs in admin menu (#1357) 2025-02-09 12:53:52 +08:00
Concedo
e68a3cf1dc fixed some functions when no model is loaded 2025-02-08 11:15:26 +08:00
Concedo
b100bcb9e6 allow ssl with remote tunnel 2025-02-08 02:11:10 +08:00
Concedo
58e2b19d56 check against platform.machine() 2025-02-08 01:20:31 +08:00
FlippFuzz
5a0ed19c96
Remote Tunnel for ARM64 Linux (#1353) 
* Update koboldcpp.py

* Fix style. Changed to double quotes to match.
 2025-02-08 01:16:30 +08:00
Concedo
cf4d0085f6 more bugfixes for admin mode 2025-02-08 01:00:52 +08:00
Concedo
b246d83dca fixed some global reference 2025-02-07 14:44:47 +08:00
Concedo
8fef9f3fb5 reloading is working correctly. 2025-02-06 22:24:18 +08:00
Concedo
080d5e6495 new admin endpoints added 2025-02-06 15:19:55 +08:00
Concedo
2c71b1b428 reworking the admin controls 2025-02-05 23:54:07 +08:00
Concedo
c6cd5943cf removed admin panel 2025-02-05 23:40:59 +08:00
Concedo
95d0ef2173 this will probably be reverted since we are changing approach 2025-02-05 22:37:21 +08:00
Concedo
72f0fdfe87 wip on hypervisor 2025-02-05 00:25:22 +08:00
Concedo
7a5499e77b added one more backend for clblast noavx2 and clblast failsafe 2025-01-30 22:47:22 +08:00
Concedo
646df4b126 default to autoguess for chat completions adapter 2025-01-30 00:25:13 +08:00
Concedo
70f1d8d746 vision can set max res (+1 squashed commits) 
Squashed commits:

[938fc655] vision can set max res
 2025-01-30 00:19:49 +08:00
Concedo
558bc5c901 tts can now set a length limit 2025-01-28 22:06:59 +08:00
Concedo
6bf0b2d062 try casting the numeric fields read 2025-01-28 17:43:28 +08:00
Concedo
0e45d3bb7a quiet flags now set at load time 2025-01-25 16:46:56 +08:00
Concedo
bec231422a Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	common/CMakeLists.txt
#	docs/backend/SYCL.md
#	docs/build.md
#	docs/docker.md
#	examples/export-lora/export-lora.cpp
#	examples/main/README.md
#	examples/main/main.cpp
#	examples/run/README.md
#	examples/run/run.cpp
#	examples/server/README.md
#	examples/simple-chat/simple-chat.cpp
#	ggml/CMakeLists.txt
#	ggml/src/ggml-hip/CMakeLists.txt
#	src/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
 2025-01-25 14:16:50 +08:00
Concedo
cca4a934dd fix for chat templates and drafting 2025-01-23 11:49:40 +08:00
Concedo
0e74db7fd4 fixed another tts bug, clblast selection and quiet mode 2025-01-22 21:36:13 +08:00
Concedo
d109d6d8eb do another patch release for the new deepseek models 2025-01-21 08:24:48 +08:00
Concedo
5329df2bdf Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/server.yml
#	CMakeLists.txt
#	cmake/build-info.cmake
#	examples/run/CMakeLists.txt
#	examples/run/run.cpp
#	examples/simple-chat/simple-chat.cpp
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-sampling.cpp
 2025-01-21 00:25:07 +08:00
Concedo
02d5bb5b05 allow smaller gguf 2025-01-20 16:20:52 +08:00
Concedo
80965bbdd7 rewritten gguf metadata reader from scratch, analyze works now 2025-01-20 15:57:03 +08:00
Concedo
5c9714cf40 improve whisper to work on 8 bit and 32bit wav too, also support form data for language 2025-01-19 16:57:41 +08:00
Concedo
fa7e661133 various fixes 2025-01-18 23:52:39 +08:00
Concedo
96407502cd Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	README.md
#	examples/llama-bench/llama-bench.cpp
#	examples/llama.android/llama/src/main/cpp/llama-android.cpp
#	examples/llama.android/llama/src/main/java/android/llama/cpp/LLamaAndroid.kt
#	src/llama-vocab.cpp
#	tests/test-backend-ops.cpp
 2025-01-17 23:13:50 +08:00
Concedo
e8570de0e6 improved tts default voices quality and sample rate 2025-01-17 18:45:16 +08:00
Concedo
8e3cad1aa2 added audio caching, as a hacky fix for ST TTS bug 2025-01-16 12:04:58 +08:00
Concedo
f8a9634aa2 better xtts and oai speech (+1 squashed commits) 
Squashed commits:

[34b9c15f] better xtts and oai speech
 2025-01-16 00:26:21 +08:00
Concedo
70ba616ecc browser launch 2025-01-15 17:41:14 +08:00
Concedo
e07de2ea92 try fix webbrowser again 2025-01-15 00:53:24 +08:00
Concedo
fec3246ca9 make mmap no longer default, archive class.py 2025-01-15 00:38:03 +08:00
Concedo
ed9f7a38ae add some built in voices 2025-01-15 00:17:17 +08:00
Concedo
0a6ccda203 better fallback browser support 2025-01-14 18:59:17 +08:00
Concedo
44720fb34c capabilities printout 2025-01-14 14:03:22 +08:00
Concedo
636beac6d2 added a nicer built in voice 2025-01-13 23:26:54 +08:00
Concedo
62e33d0bf7 added support for seeded tts voices 2025-01-13 19:11:34 +08:00
Concedo
b3de1598e7 Fixed some GGUFv1 loading bugs, long overdue cleanup for compiling, integrated TTS 
tts is functional (+6 squashed commit)

Squashed commit:

[22396311] wip tts

[3a883027] tts not yet working

[0dcfab0e] fix silly bug

[a378d9ef] some long overdue cleanup

[fc5a6fb5] Wip tts

[39f50497] wip TTS integration
 2025-01-13 14:23:25 +08:00
Concedo
12cdcf0abe improved browser opening 2025-01-11 22:53:43 +08:00
Concedo
93b2bebc2f add more options for context size 2025-01-10 19:08:42 +08:00
Concedo
0305841dd5 added a gguf file analyzer 2025-01-10 16:27:48 +08:00
Concedo
91b6e29af3 added multilingual support for whisper 2025-01-09 23:28:52 +08:00
Concedo
0cb599546e increase max supported llava images to 8 2025-01-09 22:12:06 +08:00
Concedo
c73d99ccac updated lite 2025-01-08 13:35:59 +08:00