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
7832 commits 3 branches 196 tags 386 MiB
Commit graph

932 commits

Author SHA1 Message Date
Concedo
423a68c45d multipart downloading up to 9 parts 2025-05-02 22:34:20 +08:00
Concedo
d8f1f73dd7 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build-linux-cross.yml
#	.github/workflows/build.yml
#	cmake/build-info.cmake
#	common/CMakeLists.txt
#	examples/llava/README.md
#	examples/server/README.md
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	ggml/src/ggml-vulkan/vulkan-shaders/CMakeLists.txt
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
 2025-05-02 16:54:15 +08:00
Concedo
7694cf9bfb fix rope bug (+1 squashed commits) 
Squashed commits:

[5bf69efe0] fix rope bug
 2025-05-02 16:35:01 +08:00
Concedo
bc452da452 improved comfyui compatibility, tweaked hf search 2025-05-02 16:18:31 +08:00
Concedo
803b3e1070 added HF model search tool (+1 squashed commits) 
Squashed commits:

[cbd925d59] added HF model search tool
 2025-05-02 11:44:01 +08:00
Concedo
80da6af931 wip comfyui basic websocket 2025-05-02 01:25:28 +08:00
Concedo
449382d4df use --file for yad 2025-05-01 23:48:23 +08:00
Concedo
fc255cf50c fixed null stop 2025-05-01 17:07:17 +08:00
Concedo
ed938a2fc6 increase defaultgemamt range 2025-04-30 23:13:55 +08:00
Concedo
fda682fa12 updated lite 2025-04-30 19:49:54 +08:00
Concedo
621cc8f33f think tags handling fixed 2025-04-30 14:18:37 +08:00
Concedo
c2802af9e8 fix qwen3, fixed sd, fixed glm4 2025-04-29 20:50:46 +08:00
Concedo
e659cadf48 more sanitization for user inputs 2025-04-28 15:01:50 +08:00
Concedo
a9bc1a2ee2 do not use shell true instead 2025-04-28 14:26:55 +08:00
Concedo
ca281bd5ba fix sanity check 2025-04-28 00:00:07 +08:00
Concedo
5fa9e02bc3 add debugging info to zenity check 2025-04-27 23:48:23 +08:00
Concedo
4dcd215b27 handle explicit null 2025-04-26 13:06:38 +08:00
Concedo
cb1c182673 add more warmup (+1 squashed commits) 
Squashed commits:

[9578d5352] updated lite
 2025-04-26 10:22:09 +08:00
kallewoof
7cb815b727
AutoGuess: GLM-4 (#1502) 
* AutoGuess: GLM-4

* add 'chat_start' field to adapters

* GLM-4 fix
 2025-04-26 08:47:42 +08:00
Concedo
5e87c04056 improved memory estimation (+2 squashed commit) 
Squashed commit:

[3319540f9] mem estimation

[43bad21db] mem estimation
 2025-04-26 02:03:09 +08:00
Concedo
6b6597ebf1 allow for single token prompt processing (actual batch size 1) 2025-04-25 16:54:46 +08:00
Concedo
25e747e9d8 up version 2025-04-24 18:44:29 +08:00
Concedo
3e8b84b8e5 added support for structured output in chat completions 2025-04-22 22:23:36 +08:00
Concedo
e8b3aeaa28 update some defaults for max length and max ctx 2025-04-22 15:47:01 +08:00
Concedo
6dbee2f2f8 more robust glslc checks, increase default denoise str 2025-04-22 15:19:47 +08:00
Concedo
6494dce405 handle estimation for multipart gguf (+1 squashed commits) 
Squashed commits:

[c7b4af92] handle estimation for multipart gguf
 2025-04-21 22:07:22 +08:00
Concedo
9cd6a1add2 allow mmproj to be run on cpu 2025-04-21 21:03:10 +08:00
Concedo
f968079290 randomize image names to prevent caching in noscript 2025-04-21 13:24:40 +08:00
Concedo
2ed6850c0b added override tensor 2025-04-20 20:56:17 +08:00
Concedo
75dfad2bb0 fixed noscript (+1 squashed commits) 
Squashed commits:

[dba28399] fixed noscript
 2025-04-19 23:16:08 +08:00
Concedo
12c2efdadd noscript image gen 2025-04-19 18:56:52 +08:00
Concedo
305e533dc6 i already knew zenity would cause issues 2025-04-19 13:04:41 +08:00
Concedo
78a910be26 noscript chat mode tweaks 2025-04-19 12:40:13 +08:00
Concedo
a5b5d21cca added chat mode to noscript 2025-04-19 00:59:00 +08:00
Concedo
5d57d62665 add a timeout for zenity check 2025-04-18 13:07:26 +08:00
Concedo
1a09d9cf0e increase to 10 save slots 2025-04-18 11:30:32 +08:00
Concedo
c67510718e kv override option (+1 squashed commits) 
Squashed commits:

[e615fc01] kv override option
 2025-04-17 14:22:30 +08:00
Concedo
06159939d9 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	Makefile
#	docs/build.md
#	examples/rpc/rpc-server.cpp
#	examples/sycl/build.sh
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-hip/CMakeLists.txt
#	scripts/sync-ggml.last
 2025-04-17 00:52:37 +08:00
Concedo
fbf039966c debugmode has debug in cli 2025-04-15 23:42:46 +08:00
Concedo
c168b063e5 cli fix 2025-04-15 23:30:18 +08:00
Concedo
fe12b1cbd4 fixed lora, now works quanted too 2025-04-14 23:44:42 +08:00
Concedo
6bc2ca4803 added more sanity checks on zenity 2025-04-14 15:06:08 +08:00
Concedo
3d31d75c8f clamp and display detected GPU memory 2025-04-14 14:19:23 +08:00
Concedo
a6149ad0fc fixed g3 adapter back 2025-04-12 23:17:54 +08:00
Concedo
6302709fbb discourage but dont prevent vulkan FA (it's occasionally still useful) 2025-04-12 16:23:52 +08:00
Concedo
5908f2ca19 based on occam and henky advice, disabled flash attention entirely on vulkan. 2025-04-12 12:30:48 +08:00
Concedo
7a7bdeab6d json to gbnf endpoint added 2025-04-12 11:41:11 +08:00
Concedo
a56cc72bd0 added handling for remembering file paths, added gui option to disable zenity in GUI 2025-04-12 00:42:26 +08:00
henk717
f6b7fea979
zentk - folder select workaround (#1478) 
* zentk - folder select workaround

* kcppt extention fix
 2025-04-11 22:37:07 +08:00
henk717
8fd70f37bd
Zentk integration (Zenity/yad support) (#1475) 
* Zentk integration (Zenity/yad support)

* Escape incompatible dependencies in zentk

* Properly clean env
 2025-04-11 18:23:23 +08:00