Concedo
14b7da5e44
allow reversing the reference image
2026-05-31 23:08:58 +08:00
Concedo
f90d9240f1
fixed auto gpu selection issues
2026-05-31 14:00:46 +08:00
Concedo
4cd3888e9b
increase frame limit
2026-05-31 01:30:43 +08:00
Concedo
cc9490d9b0
default embed max ctx to 4096
2026-05-31 01:23:54 +08:00
Concedo
5a4a3a34cb
allow setting backend automatically even if model is unset but sdmodel is set
2026-05-31 00:54:59 +08:00
Concedo
3361ef801c
video vae tiling fix
2026-05-30 22:59:15 +08:00
Concedo
5dc1a89001
support final frame
2026-05-30 09:27:51 +08:00
Concedo
b427dde1a5
increase total frame cap once more to 160
2026-05-30 01:34:43 +08:00
Concedo
48a6d161a5
add fps controls
2026-05-29 23:18:14 +08:00
Concedo
272c1ee232
increase frame limit to 120 and allow loading tae ltx
2026-05-29 18:50:01 +08:00
Concedo
13663730a9
ltx wip
2026-05-28 22:45:24 +08:00
Concedo
af42dc14a3
handle chat template kwargs passed by api
2026-05-28 19:25:22 +08:00
Concedo
7dbe82bb47
screen reader warning
2026-05-27 12:31:31 +08:00
Concedo
c6b32ce1f2
message for screen readers in the terminal
2026-05-27 12:17:01 +08:00
Concedo
e434b3e61b
kcpp image handling fix
2026-05-26 14:32:53 +08:00
Concedo
39a4ca08f4
alpin's cont batching is now no longer hidden, added as --parallelrequests, also added to GUI
2026-05-25 17:47:46 +08:00
Concedo
9639ab2fb6
support comfy scheduler
2026-05-25 00:22:40 +08:00
Concedo
e6715b7f8a
additional SD aliases for comfyui
2026-05-24 23:20:44 +08:00
Concedo
29fd00a7a4
allow accessing tensor split and gpu layers in cpu mode if rpc is in connect mode
2026-05-24 22:23:51 +08:00
Concedo
86f6bff620
rpc port to 5551
2026-05-24 18:56:23 +08:00
Concedo
4bbbd55be6
rpc implementation is complete
2026-05-23 17:11:30 +08:00
Concedo
81553e6524
mmproj overhead estimate calculated but only used on python side
2026-05-23 00:04:12 +08:00
Concedo
f85cc79526
make swa default on models that support it. removed --useswa, added --noswa
2026-05-22 23:38:33 +08:00
Concedo
694e8824c5
mmproj autofit reworked
2026-05-22 20:36:16 +08:00
Concedo
de6b8f9369
increase ctx slider granularity
2026-05-22 16:17:54 +08:00
Concedo
2451feaf69
an easy way to toggle thinking for jinja
2026-05-21 22:45:33 +08:00
Concedo
e8bf5b9c6c
fixed a potential vuln with onready when combined with admin
2026-05-21 16:11:28 +08:00
Wagner Bruna
f85a747dc0
sd: add backend support for max_vram ( #2221 )
2026-05-21 11:51:00 +08:00
Wagner Bruna
643862ac7d
sd: device selection fixes and improvements ( #2220 )
...
* sd: remove device offset for zero-based indexes
* sd: cleanup and document sd device mappings
* sd: change sdmaingpu control to match other sd devices
2026-05-20 15:31:19 +08:00
Concedo
b909b32135
remove off by 1 offset for sd
2026-05-20 15:23:56 +08:00
Concedo
c95d25abe2
gui visual breaking change - make GPU ID list 0-based index instead of 1-based index to match CLI
2026-05-19 22:00:43 +08:00
Wagner Bruna
592d12d0a3
sd: support for CLIP and VAE on different devices ( #2184 )
...
* sd: generalize internal interfaces to place generation on CPU
* sd: backend support for multi-device selection
* sd: frontend support for multi-device selection
* add deprecated flags to avoid breaking old cli args
---------
Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>
2026-05-19 21:51:23 +08:00
Concedo
7232096c11
Merge branch 'concedo' into concedo_experimental
...
# Conflicts:
# koboldcpp.py
2026-05-19 20:35:11 +08:00
Concedo
8bdef0bcfe
hotfix 1.113.2 bugs
2026-05-19 20:33:57 +08:00
Concedo
fecf2dc3fa
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/server-self-hosted.yml
# CMakeLists.txt
# CODEOWNERS
# ci/run.sh
# cmake/llama-config.cmake.in
# common/chat.cpp
# examples/sycl/start-svr.sh
# examples/sycl/test.sh
# examples/sycl/win-start-svr.bat
# examples/sycl/win-test.bat
# ggml/src/ggml-sycl/ggml-sycl.cpp
# ggml/src/ggml-sycl/vecdotq.hpp
# ggml/src/ggml-vulkan/CMakeLists.txt
# scripts/wc2wt.sh
# tests/test-backend-ops.cpp
# tests/test-chat.cpp
2026-05-18 21:27:23 +08:00
Concedo
de2c5f1cef
detokenize add special token ids
2026-05-17 17:04:47 +08:00
Concedo
0d320f60a6
fix multiuser regression
2026-05-17 00:17:12 +08:00
Concedo
47d5772fbe
add batching failure spam logs
2026-05-16 23:21:01 +08:00
Concedo
9203b6a051
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/labeler.yml
# .github/workflows/build-self-hosted.yml
# .github/workflows/release.yml
# .github/workflows/server-sanitize.yml
# .github/workflows/server-self-hosted.yml
# .github/workflows/server.yml
# .github/workflows/ui-build.yml
# .github/workflows/ui-ci.yml
# .github/workflows/ui-publish.yml
# .gitignore
# CMakeLists.txt
# CODEOWNERS
# scripts/ui-download.cmake
# scripts/xxd.cmake
# tests/test-backend-ops.cpp
# tests/test-reasoning-budget.cpp
# tools/CMakeLists.txt
# tools/server/CMakeLists.txt
# tools/server/README.md
2026-05-16 22:56:33 +08:00
Concedo
3095da076a
only fetch new popped horde requests if model is not blocked queue
2026-05-16 22:27:12 +08:00
Concedo
80ce8a50b3
allow token bans and eos handling in
2026-05-16 15:20:46 +08:00
Wagner Bruna
f273fd35b9
sd: sync to master-601-eeac950 ( #2206 )
...
* sd: sync to master-601-eeac950
* sd: add mmap support
2026-05-16 11:23:10 +08:00
Concedo
77fa2cd348
batching horde worker adjustments
2026-05-16 00:30:23 +08:00
Concedo
35f524d3e2
horde advertise more threads when batching is enabled
2026-05-15 17:36:53 +08:00
Reithan
5962bca463
Fix jinja error on case-insensitive roles and 0-len messages result ( #2201 )
...
* fix jinja error on case-insensitive roles and 0-len messages result
* check length in correct place
2026-05-15 16:48:42 +08:00
Concedo
1fe1a083cd
run multiple horde workers if used with batching.
2026-05-14 23:36:42 +08:00
Concedo
286e62267e
adjust batching eligibility
2026-05-11 21:54:32 +08:00
Concedo
bfaddd7a3b
added support for added memory and gemma and glm prompt fixes for batching mode
2026-05-10 23:39:03 +08:00
Concedo
33ca75d56f
ci for tools upload, minor function reordering
2026-05-10 23:10:43 +08:00
AlpinDale
c03302b670
feat: add a primitive form of continuous batching ( #2167 )
...
* feat: add a primitive form of continuous batching
* fix: deadlock in batching fallback
* fix: windows build
* chore: suppress the contbatch arg from --help
* feat: batch-aware rep_pen_slope
* fix: automatically disable shifting when batching is enabled
* fix: mixed-path state corruption
* fix: attempt to fully separate the two pipelines
* added a semaphore to prevent non-batchable requests from starting while batched requests are running
---------
Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>
2026-05-10 17:50:31 +08:00
