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
Concedo
27f575dc83
inpaining support completed, invert mask added
2025-04-09 23:50:17 +08:00
Concedo
23339ace9b
inpainting works in kcpp!
2025-04-09 23:01:05 +08:00
Concedo
26e1653255
fixed templates not setting gpu when swapped with admin mode
2025-04-08 21:45:18 +08:00
Concedo
b99ee451f8
Merge commit ' 4ccea213bc' into concedo_experimental
...
# Conflicts:
# .devops/cpu.Dockerfile
# .devops/cuda.Dockerfile
# .devops/intel.Dockerfile
# .devops/musa.Dockerfile
# .devops/rocm.Dockerfile
# .github/workflows/bench.yml.disabled
# .github/workflows/build.yml
# .github/workflows/server.yml
# CMakeLists.txt
# build-xcframework.sh
# ci/run.sh
# common/CMakeLists.txt
# examples/llama.android/llama/build.gradle.kts
# examples/perplexity/perplexity.cpp
# examples/run/CMakeLists.txt
# examples/server/tests/README.md
# examples/sycl/win-build-sycl.bat
# ggml/src/ggml-cann/aclnn_ops.cpp
# ggml/src/ggml-cann/aclnn_ops.h
# ggml/src/ggml-cpu/CMakeLists.txt
# ggml/src/ggml-cpu/ggml-cpu.c
# licenses/LICENSE-linenoise
# scripts/sync-ggml.last
# tests/CMakeLists.txt
2025-04-08 21:26:23 +08:00
Concedo
8e23a087e7
updated readme, memory detection prints
2025-04-08 20:23:52 +08:00
Concedo
11c4e7c2c4
automatic memory detection for vulkan
2025-04-07 22:56:12 +08:00
Concedo
11f993ca10
added flag to adjust max request size
2025-04-06 00:13:00 +08:00
Concedo
65cd25d3a1
some data sanitization
2025-04-05 18:42:26 +08:00
Concedo
93a226d9e4
added prefix for llava, reverted system role in template as it degreaded gemma3. truncated debug logs
2025-04-05 18:06:41 +08:00
Concedo
34ddd874fe
try containerized ci (+3 squashed commit)
...
Squashed commit:
[f0600744fe11073c0c7f8a1d
2025-04-05 01:51:03 +08:00
Concedo
c48a4a73d4
try fix file open
2025-04-04 14:38:17 +08:00
Concedo
43e9b049d6
another silly bug silly silly silly (tavern)
2025-04-04 14:16:42 +08:00
Concedo
07a96d63fa
try to ensure correct file extension
2025-04-03 20:13:53 +08:00
Concedo
6e086bd309
fixed savedatafile bug, try remove unneeded old clblast code path
2025-04-03 19:11:27 +08:00
Concedo
7f1003be44
warning for max tokens being too high
2025-04-02 18:58:38 +08:00
Concedo
fbf5c04c3c
silly me
2025-04-02 00:51:05 +08:00
Concedo
30e3d24ead
embd include name
2025-04-02 00:40:38 +08:00
Concedo
e37f27632f
clear cpu flag manually for templates, added truncation for embeddings
2025-04-02 00:18:30 +08:00
Concedo
0fd94e19f3
made tool calls more robust and allowed tool call template customization
2025-04-01 19:16:45 +08:00
henk717
4291e1575b
Fix tool spec, this spec is kinda.... ( #1458 )
2025-04-01 10:39:02 +08:00
Concedo
c0adaabfa4
Revert "try fix owui"
...
This reverts commit 12e5b8abdb
2025-04-01 00:27:31 +08:00
Concedo
12e5b8abdb
try fix owui
2025-04-01 00:23:45 +08:00
Concedo
0ed95fcccc
fixed l3 template, add index
2025-03-31 23:59:06 +08:00
Concedo
1ebadc515e
add streaming support for oai tools (+2 squashed commit)
...
Squashed commit:
[4d080b37] qwen2.5vl surgery script
[4bebe7e5] add streaming support for oai tools
2025-03-31 16:49:15 +08:00
henk717
091eb367fc
More robust tool calling prompt ( #1455 )
...
* More robust tool checking prompt
* Inform UI we want a tool
2025-03-31 14:43:03 +08:00
Concedo
b4a8a5a278
Added CLI chat mode
...
minor cli fixes (+1 squashed commits)
Squashed commits:
[60af39a9] Added CLI chat mode
2025-03-26 21:01:58 +08:00
Concedo
2bdf1dacff
embeddings done
2025-03-25 22:41:46 +08:00
Concedo
82f2654049
wip embeddings model
2025-03-25 00:18:02 +08:00
Concedo
3992fb79cc
wip adding embeddings support
2025-03-24 18:01:23 +08:00
Concedo
b1641ee4a2
allow quant K without quant V but with a warning (+1 squashed commits)
...
Squashed commits:
[45408dd9] allow quant K without quant V but with a warning
2025-03-23 22:56:02 +08:00
Concedo
a20a29ddeb
tool calling improved, auto now works
2025-03-22 17:44:55 +08:00
Concedo
350427dc3a
adjust subprocess timeouts
2025-03-22 11:10:01 +08:00
InconsolableCellist
e31da5861a
1435: add timeout for vulkaninfo ( #1436 )
...
* Fix the Colab PR
* 1435: add timeout for vulkaninfo
There's a bug in vulkaninfo where it can hang, and this will prevent
koboldcpp from starting. This adds a 5 second timeout
* restoring colab.ipynb
* Formatting
---------
Co-authored-by: henk717 <henk@henk.tech>
2025-03-22 11:01:22 +08:00
Concedo
c1e58419c7
support for voice cloning is done (+2 squashed commit)
...
Squashed commit:
[e7301628] support for voice cloning is done
[1653c576] wip adding voice cloning
2025-03-21 22:28:59 +08:00
Concedo
a66d0f7743
safeguard for bad vision input
2025-03-20 22:20:38 +08:00
Concedo
9d5efd68b6
dont print full base64 for images
2025-03-20 21:20:04 +08:00
