cfb22b5c9d
rename a missed BLAS -> batch
2025-11-06 16:11:26 +08:00
978d755ddc
escape clause for tool calling
2025-11-05 22:02:24 +08:00
3e4a33499f
updated lite
2025-11-05 20:52:47 +08:00
6ddacb62a0
serve gzipped versions of files. added a modded lcpp gui with modified path handling and proper stream termination, see https://github.com/ggml-org/llama.cpp/pull/14839#issuecomment-3490987929
2025-11-05 20:40:30 +08:00
333e2bb30b
fix for qwen image crashing due to ref images being too big, trial and error shows it happens after 512x512
2025-11-02 01:31:01 +08:00
988baa544e
add JobRate and JobCost to worker log ( #1820 )
...
- adds average jobs per hour
- adds average kudos earned per job
- change EarnRate to show 2 decimal places
2025-11-01 10:01:13 +08:00
d229774e11
added compatibility endpoint for VITS api
2025-10-26 17:35:10 +08:00
b730c99ecb
fixed a typo
2025-10-26 10:06:59 +08:00
57e1d9c822
rename blasbatchsize to batchsize
2025-10-24 18:16:54 +08:00
68c9d955d2
support multiple override kv
2025-10-24 17:28:54 +08:00
7446e03851
send logprobs in streaming for oai
2025-10-21 18:23:56 +08:00
7d20e6bdb3
updated layer count to be more accurate +1 instead of +3
2025-10-18 15:29:07 +08:00
f6916ba864
updated sdui
2025-10-17 13:56:45 +08:00
45a02ae534
rename blas to just batching
2025-10-16 16:27:51 +08:00
4eaf05dfeb
handle oai without v1 prefix
2025-10-16 02:16:49 +08:00
dfeccea3a1
added shitty fractional scaling support for GNOME. but really just use KDE
2025-10-15 22:28:04 +08:00
8b787866c6
fixed a typo
2025-10-13 11:14:38 +08:00
1a360b8458
sdcpp: optimize the handling of the FeedForward precision fix (+1 squashed commits)
...
Squashed commits:
[621ff6392] sdcpp: optimize the handling of the FeedForward precision fix (+1 squashed commits)
Squashed commits:
[05b16906c] sdcpp: optimize the handling of the FeedForward precision fix
2025-10-12 17:49:38 +08:00
a0ed446e61
handle numbers outside int32 range with wrapping
2025-10-12 12:46:45 +08:00
9f9494cf3f
sd: add 'default' to the list of supported samplers ( #1788 )
2025-10-12 12:35:56 +08:00
5396e62b56
allow resetting missing fields to default
2025-10-09 23:36:38 +08:00
96dfa7a038
sdgendefaults follow all other params
2025-10-09 14:57:34 +08:00
c1a246c1de
fixed typo
2025-10-07 21:51:15 +08:00
2fa28fdcf8
wrap sd_parse_meta_field in trycatch
2025-10-06 00:05:19 +08:00
c48999f7c0
additional options for image generation ( #1765 )
...
* sd: add backend support for choosing the default sampler
* use the default sampler on the API
* sd: add backend support for the scheduler
* sd: add backend support for distilled guidance
* sd: add backend support for timestep-shift
* sd: add a config field to set default image gen options
2025-10-05 23:36:20 +08:00
a09d8333b5
allow lowvram (nkvo) to be used with vulkan.
2025-10-05 16:18:58 +08:00
f282362414
added qwen image support (+1 squashed commits)
...
Squashed commits:
[92df28061] added qwen image support (+1 squashed commits)
Squashed commits:
[1485c71ed] wip adding qwen image
2025-10-03 18:58:48 +08:00
4f8f0e5949
move embeds into their own dir, detach sd vocab into separate files
2025-10-03 14:21:09 +08:00
539db70eac
clip to cpu by default
2025-10-02 10:56:51 +08:00
2fc31d36c0
gif mime type for animated images
2025-10-01 17:18:00 +08:00
b3a0ba5e37
adjust max frames
2025-09-30 17:43:27 +08:00
4b1c89ca5c
can save animated gifs
2025-09-29 22:52:42 +08:00
7b71742223
added additional toggles for SD, sdoffloadcpu , sdvaecpu and sdclipcpu
2025-09-28 22:08:29 +08:00
553890f975
compact UI launcher, WIP handling video outputs
2025-09-28 17:24:04 +08:00
3326bdc00a
if blank, autoguess template
2025-09-27 12:49:32 +08:00
c7a1eec4e4
try to solve ttscpp oom regression
2025-09-24 17:45:28 +08:00
d3f9db8d33
fix system32 writability check
2025-09-24 14:43:41 +08:00
174d00bb74
fix aria2c with both download cases
2025-09-22 21:47:08 +08:00
59b6a09ae1
try to fix kokoro alloc again
2025-09-22 21:22:41 +08:00
216b766aee
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build-riscv-native.yml
# .github/workflows/build.yml
# ci/README.md
# ci/run.sh
# ggml/src/ggml-opencl/CMakeLists.txt
# ggml/src/ggml-opencl/ggml-opencl.cpp
# ggml/src/ggml-opencl/kernels/cvt.cl
# tests/test-backend-ops.cpp
2025-09-22 13:56:02 +08:00
08c0246f24
prioritize cwd for downloads if its writable
2025-09-22 13:47:50 +08:00
13bee0d39d
some minor fixes
2025-09-22 13:20:06 +08:00
c8686a627e
don't mandate mistral common for other model usage
2025-09-21 21:16:02 +08:00
9e7661352c
Revert "FA default on"
...
This reverts commit 19c3efb34a
2025-09-21 17:28:49 +08:00
19c3efb34a
FA default on
2025-09-14 11:53:18 +08:00
bf8fc4659b
updated lite, tweak default rep pens, default fa off (+3 squashed commit)
...
Squashed commit:
[be2b10125] default rep pen 1.05
[cb4527b15] better to default fa off
[126104fe7] updated lite
2025-09-14 00:11:52 +08:00
89feffc0e4
fix aria2c
2025-09-06 09:45:14 +08:00
f9ce2a00f0
consistent file download locations
2025-09-06 09:26:45 +08:00
979e2113e2
flash attention is now checked by default when using gui launcher
2025-09-03 23:36:43 +08:00
5c4ad392ea
added a new parameter --ratelimit that will apply per-IP based rate limiting (to help prevent abuse of public instances).
2025-09-01 22:08:13 +08:00
LostRuins Concedo
xzuyn
Wagner Bruna