10bf868088
try improve mcp
2026-02-10 15:33:39 +08:00
9a33257742
prevent download dir being changed by config
2026-02-09 16:43:04 +08:00
098af866dd
fractional scale adjust
2026-02-08 15:32:02 +08:00
6ded3f04e4
patch for output filenames
2026-02-08 13:05:52 +08:00
5962330dde
-1 layer triggers autofit if tensor split and override tensors is not set
2026-02-07 22:31:01 +08:00
404b5fe659
wip reworking auto mode
2026-02-07 19:33:50 +08:00
5cf21443bc
added autofit padding. autofit is now in the quick menu
2026-02-07 18:29:30 +08:00
78bba94f72
autofit hides gpu layer inputs entirely
2026-02-07 17:17:19 +08:00
bab1c4ca50
proper handling of common think tags in lcpp ui jinja mode
2026-02-07 17:05:21 +08:00
a0a78dacc4
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# docs/ops.md
# docs/ops/SYCL.csv
# ggml/src/ggml-sycl/element_wise.cpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
# ggml/src/ggml-webgpu/ggml-webgpu.cpp
# pyproject.toml
# requirements/requirements-convert_legacy_llama.txt
# src/CMakeLists.txt
# src/llama-vocab.cpp
# tests/test-backend-ops.cpp
2026-02-07 15:54:02 +08:00
3d99b87506
add downloaddir
2026-02-06 14:34:02 +08:00
de3ed7d7d6
add missing resolve_refs call to enable subschema use ( #1959 )
2026-02-05 22:12:59 +08:00
ceb548f407
update text (+1 squashed commits)
...
Squashed commits:
[2a1532783] update text
2026-02-05 22:11:10 +08:00
0e907e23fb
Revamped help menu
2026-02-05 17:34:39 +08:00
30c74d5cce
fixed mcp bug
2026-02-04 20:46:55 +08:00
4b073f3aa0
fix sse parsing in mcp
2026-02-04 20:38:33 +08:00
349c461453
add stop reason for error
2026-02-04 20:23:18 +08:00
d9ac52a01a
sd: sync to master-492-f957fa3 ( #1957 )
...
* sd: sync to master-492-f957fa3
* add Res Multistep and Res 2s samplers
* make sdflashattention control flash_attn too
2026-02-04 16:12:39 +08:00
dfa725c58d
make the dpi fix more universal. not a perfect solution
2026-02-03 19:49:38 +08:00
b13bf44285
kde fractional scaling fix, tooltip fix (+1 squashed commits)
...
Squashed commits:
[1cf02dcce] kde fractional scaling fix
2026-02-01 21:55:44 +08:00
9ef5d34740
fix mcp cert issues
2026-02-01 16:48:37 +08:00
ffdc1b0f9f
flux2 image editing
2026-01-31 16:36:45 +08:00
66e1913da6
fix blocked UA for mcp
2026-01-29 23:53:50 +08:00
5c29510330
mcp try handle vscode
2026-01-29 23:39:36 +08:00
cd6e087eeb
include kde in the fractional scaling fix
2026-01-29 22:06:21 +08:00
deee1c2cfc
fixed mcp stdio server tool listing ( #1950 )
2026-01-29 21:35:35 +08:00
ef7fe1b5d4
make flash attention default in cli. added --noflashattention
2026-01-28 23:28:48 +08:00
fec0d2bb4a
pipeline parallel is default in cli now
2026-01-25 18:16:58 +08:00
7f485e5287
remove CLBlast, part 1
2026-01-23 13:50:12 +08:00
28091dec43
pipeline parallel default enable
2026-01-21 17:57:41 +08:00
cdd6578a9a
esrgan added
2026-01-20 22:10:37 +08:00
c9c15749e0
wip on adding esrgan upscaling
2026-01-20 00:35:35 +08:00
d827494f17
fix text for vae (+1 squashed commits)
...
Squashed commits:
[793caed19] fix text
2026-01-19 01:50:07 +08:00
7f618454ff
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/labeler.yml
# CODEOWNERS
# docs/backend/OPENCL.md
# docs/ops.md
# docs/ops/CANN.csv
# docs/ops/WebGPU.csv
# ggml/src/ggml-blas/CMakeLists.txt
# ggml/src/ggml-opencl/kernels/mul_mv_q6_k.cl
# ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
# ggml/src/ggml-webgpu/ggml-webgpu.cpp
# ggml/src/ggml-webgpu/wgsl-shaders/cpy.tmpl.wgsl
# ggml/src/ggml-webgpu/wgsl-shaders/set_rows.wgsl
# tests/test-backend-ops.cpp
2026-01-18 23:24:29 +08:00
95ebfdcde8
Add token ids to logprob data returned by the API ( #1928 )
...
Previously, logprobs only contained the token string
and byte data, as well as the log probability itself.
For workflows that require the token id, translating
from the token bytes to the token id is potentially
costly and unreliable. It is simple and inexpensive
to expose the numeric token ids directly instead.
2026-01-18 16:30:46 +08:00
7b4517c2fe
embeddings memory usage regression fix
2026-01-18 16:26:52 +08:00
3816391a74
increase logprobs returned to 10
2026-01-18 11:13:42 +08:00
22ddad81b9
device override set in gui
2026-01-18 10:54:20 +08:00
89a205ecc7
bump version
2026-01-17 19:09:14 +08:00
62bea5ef4f
allow overriding the devices directly
2026-01-17 19:08:06 +08:00
8855a7f52b
Merge commit 'c945aaaef298ddb3eed72d36e45d6b3a2a1abd75' into concedo_experimental
...
# Conflicts:
# .devops/cann.Dockerfile
# .github/workflows/build.yml
# .github/workflows/release.yml
# README.md
# common/CMakeLists.txt
# common/chat.cpp
# docs/function-calling.md
# ggml/src/ggml-cann/aclnn_ops.cpp
# ggml/src/ggml-cann/aclnn_ops.h
# ggml/src/ggml-cann/common.h
# ggml/src/ggml-cann/ggml-cann.cpp
# models/templates/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.jinja
# scripts/sync_vendor.py
# tests/CMakeLists.txt
# tests/peg-parser/tests.h
# tests/test-chat-peg-parser.cpp
# tests/test-chat-template.cpp
# tests/test-chat.cpp
# tests/testing.h
# tools/llama-bench/llama-bench.cpp
2026-01-17 10:24:03 +08:00
a5204d2363
fixed mcp command location
2026-01-17 00:09:46 +08:00
c332bb614c
better mcp error messages
2026-01-16 17:55:34 +08:00
612c19afe7
interrogate max length increased
2026-01-13 11:06:05 +08:00
3752040165
default to continue assistant turns
2026-01-12 23:12:27 +08:00
fc51d8b216
fix prop type for tools
2026-01-12 18:28:00 +08:00
4bf6d9eb9a
trying with fa on by default
2026-01-07 11:38:45 +08:00
3108fe740c
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# docs/ops.md
# docs/ops/WebGPU.csv
# examples/model-conversion/logits.cpp
# examples/retrieval/retrieval.cpp
# ggml/src/ggml-cann/ggml-cann.cpp
# ggml/src/ggml-webgpu/ggml-webgpu.cpp
# ggml/src/ggml-webgpu/wgsl-shaders/unary_op.wgsl
2026-01-06 20:49:01 +08:00
bd51d775be
Merge branch 'concedo' into concedo_experimental
2026-01-05 21:04:42 +08:00
1fc405b8b6
1.105.4
2026-01-05 21:01:42 +08:00
Concedo
Reithan
Wagner Bruna
Rose
Llama