Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity
12,274 Commits 3 Branches 254 Tags
98f099aecc9ca4ff7a3a619a6d1dfe639b009b91
Commit Graph

12274 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Concedo 98f099aecc Merge commit 'c1258830b28dddc65ac3aa3452214553fdece30c' into concedo_experimental 
# Conflicts:
#	docs/docker.md
#	docs/ops.md
#	docs/ops/WebGPU.csv
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/get_rows.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/row_norm.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/unary.wgsl
 2026-03-21 12:00:52 +08:00
Concedo 07327b6c10 double n_batch size when pipeline parallel is enabled, keep u_batch the same 2026-03-21 11:22:10 +08:00
Concedo 3113e3a643 move main device print 2026-03-21 10:47:21 +08:00
Concedo 9ba8c7a661 fixed colab 2026-03-21 10:21:18 +08:00
Concedo 1225b1b155 add nothink autoguess 2026-03-20 21:21:06 +08:00
Concedo 2d349723d3 fixed colab 2026-03-20 18:19:59 +08:00
Gustavo Rocha Dias 8e045b33a1 fix - w64devkit vulkan build (#2048) 2026-03-20 16:37:22 +08:00
Concedo d6aae073b6 fixed typo 2026-03-20 12:02:04 +08:00
Concedo 1f73eabb46 fixed colab 2026-03-20 11:45:10 +08:00
Reese Levine c1258830b2 ggml webgpu: ops support for qwen3.5 (SET, TRI_SOLVE, SSM_CONV, GATED_DELTA_NET) + GET_ROWS optimization (#20687) 
* Implement l2_norm, set, tri

* Add DIAG/SOLVE_TRI

* Add SSM_CONV

* Better get_rows and gated_delta_net to support qwen3.5

* Clean up, update ops.md

* Fix binding_index type for wasm

* Fix read write annotations

* cleanups
 2026-03-19 08:45:28 -07:00
ddh0 922b90e567 common : add LLAMA_ARG_SPEC_TYPE (#20744) 2026-03-19 16:16:55 +01:00
Concedo c4b1a17e1a tools debug 2026-03-19 23:13:02 +08:00
Georgi Gerganov f071ce67c9 ci : add action for finding duplicate issues (#20756) 
* ci : add action for finding duplicates issues

* cont : gen info

* cont : formatting

* cont : fix

* cont : instructions

* cont : bump checkout action

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2026-03-19 16:17:37 +02:00
Pascal 4065c1a3a6 Server becomes the source of truth for sampling parameter defaults (#20558) 
* webui: make server the source of truth for sampling defaults

* webui: fix Custom badge for sampling parameters

* webui: log user overrides after server sync

* chore: update webui build output

* fix: Default values for sampling settings config object

* chore: update webui build output

---------

Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com>
 2026-03-19 13:20:39 +01:00
Xuan-Son Nguyen 1e64534570 mtmd: add clip_graph::build_mm() (#20751) 
* clip: add build_mm()

* apply to all models

* add TODO for bias overload
 2026-03-19 13:11:39 +01:00
Pascal cd708db0cc WebUI: Persist the on/off state of the MCP servers for new conversations (#20750) 
* webui: add persistent storage for MCP server on/off state in new chats

* webui: simplify MCP enabled checks, remove dead server.enabled fallback

* chore: update webui build output

* chore: update webui build output

---------

Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com>
 2026-03-19 12:54:06 +01:00
Aleksander Grygier 512bba6ee0 webui: Improve model parsing logic + add unit tests (#20749) 
* add tests for model id parser

* add test case having activated params

* add structured tests for model id parser

* add ToDo

* feat: Improve model parsing logic + tests

* chore: update webui build output

---------

Co-authored-by: bluemoehre <bluemoehre@gmx.de>
 2026-03-19 12:25:50 +01:00
Dowon b486c17b3e convert : support is_causal hyperparameter (#20746) 
* convert : support is_causal hyperparameter

Check for the `is_causal` attribute in the Hugging Face model configuration and include it in the GGUF metadata.

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* style: fix F541 f-string is missing placeholders

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2026-03-19 11:41:11 +01:00
Aldehir Rojas 1b9bbaa357 common : fix gpt-oss content removal (#20745) 2026-03-19 11:40:39 +01:00
Eve 07feeaa92e vulkan: dequantize iq4_xs 4 at a time (#20657) 2026-03-19 11:32:04 +01:00
Charles Xu 3fee84e156 cmake : fix build warning when kleidiai is enabled (#20457) 
* cmake : fix build warning when kleidiai is enabled

* remove LLAMA_ARG_THREADS from KleidiAI backend
 2026-03-19 10:14:48 +02:00
Sigbjørn Skjæret 811397745e vocab : assert array size of scores and toktypes (#20737) 2026-03-19 08:34:04 +01:00
Kevin Hannon c014c3f83a docs: add information about openvino in the docker page (#20743) 2026-03-19 15:08:47 +08:00
Concedo 699bc6b278 github actions updates for deprecation of nodejs 20 (+1 squashed commits) 
Squashed commits:

[0ed5af384] checkout to v4
v1.110 		2026-03-19 14:39:43 +08:00
Chenguang Li 7f2cbd9a4d CANN: handle in-place ROPE on non-contiguous f32 tensors (#20274) 
RotaryPositionEmbedding on CANN fails when src and dst share the same
non-contiguous buffer (inplace + view), because the operator overwrites
source data before it is fully read.

Add a branch that detects this case and uses contiguous temporary
buffers: copy src to temp, run ROPE into another temp, then copy back
to the non-contiguous dst. Fixes 20 failing ROPE tests (f32, v=1,
inplace=1).

Signed-off-by: noemotiovon <757486878@qq.com>
 2026-03-19 14:05:01 +08:00
Concedo 2f63f94fd8 fix router nocertify mode 2026-03-19 12:45:19 +08:00
Concedo 8cf9ba34e9 fixed SSL in routermode 2026-03-19 12:43:11 +08:00
Masashi Yoshimura 509a31d00f ggml-webgpu: Update the RMS_NORM preprocessor and add L2_NORM (#20665) 
* Update the preprocessor of RMS_NORM and add L2_NORM.

* Fix the name of rms_norm to row_norm.
 2026-03-18 21:08:59 -07:00
Masashi Yoshimura ea01d196d7 ggml-webgpu: Add supports for DIAG and TRI (#20664) 
* Add supports for DIAG and TRI.

* Remove extra ttype and add a comment for TRI op.
 2026-03-18 21:08:35 -07:00
Chenguang Li 07ba6d275b CANN: support flash attention for head dim not multiple of 16, fix ALiBi slope offset (#20031) 
- Allow FLASH_ATTN_EXT when head dimension D is not a multiple of 16 by
  padding Q/K/V to D_padded = GGML_PAD(D, 16), running FusedInferAttentionScoreV2,
  then slicing the output back to D (ggml-cann.cpp + aclnn_ops.cpp).
- Fix aclnn_get_slope second-part offset: use ggml_type_size(dtype) instead of
  sizeof(float) so ALiBi slopes are correct when dtype is F16 (e.g. GQA with
  48 heads); fixes buffer overflow and large numerical errors in those cases.
 2026-03-19 11:02:42 +08:00
Michael Grau 6729d4920c model : add control vector support where missing (#20653) 
* Add control vector functions to qwen3.5 and qwen-next models

* Add missing cvec compatibility to the rest of the models

* Adjust comments and formatting

* cleanup

* whitespace

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2026-03-18 23:25:12 +01:00
Sigbjørn Skjæret d13d60af1d gguf-py : cleaner way to get the first key (#20727) 2026-03-18 23:21:42 +01:00
Concedo 48f914e374 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	ci/run.sh
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/arch/riscv/repack.cpp
#	ggml/src/ggml-cpu/arch/x86/repack.cpp
#	ggml/src/ggml-cpu/repack.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/htp-msg.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-base.h
#	ggml/src/ggml-hexagon/htp/hvx-exp.h
#	ggml/src/ggml-hexagon/htp/hvx-sigmoid.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/softmax-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	scripts/sync-ggml.last
#	tests/test-backend-sampler.cpp
#	tests/test-chat.cpp
#	tests/test-jinja.cpp
#	tools/cli/cli.cpp
 2026-03-19 02:23:06 +08:00
crsawyer 5744d7ec43 Rebuild index.html.gz (#20724) 2026-03-18 18:49:57 +01:00
Reese Levine 8ced5f41f9 Move to no timeout for WaitAny in graph submission to avoid deadlocks in some cases on llvm-pipe backends (#20618) 2026-03-18 10:23:47 -07:00
Shaw Nguyen 78d550b541 ggml-cpu/x86: fix unused changemask warning in repack (#20692) 2026-03-18 18:45:06 +02:00
Concedo 15e86010d8 autofit will clear moecpu and overridetensors 2026-03-18 21:20:57 +08:00
Georgi Gerganov 4efd326e71 sync : ggml 2026-03-18 15:17:28 +02:00
Georgi Gerganov b08f7322ee ggml : bump version to 0.9.8 (ggml/1442) 2026-03-18 15:17:28 +02:00
Georgi Gerganov 79187f2fb8 ggml : restore ggml_type_sizef() to aboid major version bump (ggml/1441) 2026-03-18 15:17:28 +02:00
Julien Chaumond 48e61238e1 webui: improve tooltip wording for attachment requirements (#20688) 
* webui: improve tooltip wording for attachment requirements

Co-Authored-By: Claude <Agents+claude@huggingface.co>

* chore: update webui build output

* chore: update webui build output

---------

Co-authored-by: Claude <Agents+claude@huggingface.co>
 2026-03-18 14:01:02 +01:00
Pop Flamingo 312cf03328 llama : re-enable manual LoRA adapter free (#19983) 
* Re-enable manual LoRA adapter free

* Remove stale "all adapters must be loaded before context creation" stale comments
 2026-03-18 12:03:26 +02:00
Masato Nakasaka f4049ad735 tests : fix test-jinja-py Windows failures by bypassing command-line args [no ci] (#20483) 
* Fix errors occurring on Windows

* Reverted fix

#20365 will take care of CRLF isue

* Changed to write to directly to stdin

* Prevent fclose to happen twice
 2026-03-18 10:43:31 +01:00
Aldehir Rojas 5e8910a0db common : rework gpt-oss parser (#20393) 
* common : rework gpt-oss parser

* cont : fix gpt-oss tests

* cont : add structured output test

* cont : rename final to final_msg
 2026-03-18 10:41:25 +01:00
Aaron Teo fe00a84b4b tests: enable kv_unified to prevent cuda oom error on rtx 2060 (#20645) 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2026-03-18 17:40:22 +08:00
Aleksander Grygier 7ab321d40d webui: Fix duplicated messages on q param (#20715) 
* fix: Remove duplicate message sending on `?q` param

* chore: update webui build output
 2026-03-18 10:32:43 +01:00
uvos 7533a7d509 HIP : ignore return of hipMemAdvise [no ci] (#20696) 2026-03-18 09:53:13 +01:00
Andreas Obersteiner a69d54f990 context : fix graph not resetting when control vector changes (#20381) 2026-03-18 08:10:13 +02:00
Concedo f8aa711e5c musicui seed randomizer 2026-03-18 11:28:46 +08:00
Concedo f796878022 updated lite 2026-03-18 11:20:32 +08:00