vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-22 03:10:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
9077 commits 3 branches 240 tags 1.3 GiB
Commit graph

9077 commits

This branch
This branch
All branches
Author SHA1 Message Date
Concedo
4c1faf61b2 increment version (+1 squashed commits) 
Squashed commits:

[6e5080ad2] increment version
 2025-08-09 20:53:26 +08:00
Concedo
0fb25bb165 Merge branch 'upstream' into concedo_experimental 2025-08-09 20:31:36 +08:00
Concedo
5f95fc1122 update lite 2025-08-09 20:31:15 +08:00
Aman Gupta
34c9d765bf
CUDA: add attention sinks for tile and wmma (#15178) 
* CUDA: add attention sinks for tile and wmma

* Review: formatting changes + remove syncthreads from tile + remove warp_reduce_max from wmma
 2025-08-09 20:00:24 +08:00
Concedo
ced98823a1 kai api tool calling 2025-08-09 10:51:10 +08:00
Concedo
4c7b82e982 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	scripts/server-bench.py
 2025-08-09 10:34:24 +08:00
Concedo
fc551470d4 updated lite 2025-08-09 10:33:59 +08:00
compilade
e54d41befc
gguf-py : add Numpy MXFP4 de/quantization support (#15111) 
* gguf-py : add MXFP4 de/quantization support

* ggml-quants : handle zero amax for MXFP4
 2025-08-08 17:48:26 -04:00
Johannes Gäßler
4850b52aed
server-bench: external OAI servers, sqlite (#15179) 
* server-bench: external OAI servers, sqlite

* Update scripts/server-bench.py

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

* Update scripts/server-bench.py

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

* Update scripts/server-bench.py

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

* raise_for_status

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-08-08 23:04:36 +02:00
Concedo
9e7a940ce4 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/softmax_4_f16.cl
#	ggml/src/ggml-opencl/kernels/softmax_4_f32.cl
#	ggml/src/ggml-opencl/kernels/softmax_f16.cl
#	ggml/src/ggml-opencl/kernels/softmax_f32.cl
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
 2025-08-09 01:24:52 +08:00
Concedo
7087aeb4bc anti bsod only for nvidia 2025-08-09 01:23:38 +08:00
Concedo
67e0072245 fixed clblast repacking 2025-08-09 01:08:02 +08:00
Concedo
3468c2834d fixed adv mode 2025-08-08 22:26:36 +08:00
kallewoof
866cc346ab
tweak OpenAI Harmony autoguess developer prefix and assistant end token (#1673) 
* tweak OpenAI Harmony autoguess developer prefix

* use <|end|> for adapter end
 2025-08-08 21:15:11 +08:00
AN Long
cd6983d56d
ggml : fix field name when new ggml_backend (#14944) 2025-08-08 14:37:22 +02:00
Olivier Chafik
6c7e9a5440
vendor: sync minja (#15161) 
* vendor: sync minja

* Update minja.hpp

* Apply suggestions from code review

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

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-08-08 10:45:18 +01:00
Johannes Gäßler
1425f587a8
CUDA: attention sinks for mma FlashAttention (#15157) 2025-08-08 08:19:58 +02:00
lhez
aaa3d07ae7
opencl: support sink in soft_max (attn sinks) (#15152) 2025-08-07 21:47:03 -07:00
Concedo
d5b5e79035 should fix vulkan bsod 2025-08-08 10:57:50 +08:00
Wagner Bruna
eed5577aaa
fix unintended sd model quantization (#1672) 
The recent ggml update added another quant type, GGML_TYPE_MXFP4,
which got the same value as SD_TYPE_COUNT. That made the embedded
sd.cpp quantize to GGML_TYPE_MXFP4 by default.

Photomaker in particular ends up crashing due to
"Missing CPY op for types: f32 mxfp4".
 2025-08-08 10:19:58 +08:00
Xuan-Son Nguyen
50aa938901
convert : support non-mxfp4 HF model (#15153) 
* convert : support non-mxfp4 HF model

* rm redundant check

* disable debug check
 2025-08-07 23:26:03 +02:00
Jeff Bolz
c4f53563df
vulkan: support fattn sinks (#15126) 2025-08-07 22:44:20 +02:00
Jeff Bolz
a0552c8bee
vulkan: Add env var to disable host visible vidmem (#15109) 2025-08-07 22:07:11 +02:00
RunningLeon
99acbc9921
llama : Support intern-s1 (#14875) 
* support internvl

* support interns1

* resolve comments

* put interns1 in tensor mapping

* resolve comment

* move tokenizer changes to sub class
 2025-08-07 18:20:40 +02:00
Concedo
8f15461bea updated lite 2025-08-08 00:04:47 +08:00
uvos
7ad67ba9fe
HIP: add cmake option to enable compiler output of kernel resource usage metrics (#15103) 2025-08-07 16:44:14 +02:00
Concedo
8a71eb03c0 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	ggml/cmake/ggml-config.cmake.in
#	ggml/src/ggml-cann/CMakeLists.txt
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cuda/fattn.cu
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	requirements/requirements-convert_hf_to_gguf.txt
#	scripts/compare-llama-bench.py
#	tests/test-chat-template.cpp
#	tests/test-chat.cpp
#	tools/llama-bench/llama-bench.cpp
 2025-08-07 21:23:09 +08:00
Concedo
338b1fe97e readjusted mistral and oai template, fixed compile issue on termux, updated lite, show generated token ids in debug mode 2025-08-07 21:14:48 +08:00
Christian Kastner
9a96389544
ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 
Any available libraries are found and loaded dynamically at runtime.
 2025-08-07 13:45:41 +02:00
Johannes Gäßler
1d72c84188
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 (#15131) 
* CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16
 2025-08-07 10:53:21 +02:00
Johannes Gäßler
20638e4f16
scripts: fix crash when --tool is not set (#15133) 2025-08-07 08:50:30 +02:00
Daniel Bevenius
36d3f00e14
requirements : fix PyTorch uint64 compatibility (#15134) 
This commit addresses an issue with the convert_hf_to_gguf script
which is currently failing with:
```console
AttributeError: module 'torch' has no attribute 'uint64'
```

This occurred because safetensors expects torch.uint64 to be available
in the public API, but PyTorch 2.2.x only provides limited support for
unsigned types beyond uint8 it seems. The torch.uint64 dtype exists but
is not exposed in the standard torch namespace
(see pytorch/pytorch#58734).

PyTorch 2.4.0 properly exposes torch.uint64 in the public API, resolving
the compatibility issue with safetensors. This also required torchvision
to updated to =0.19.0 for compatibility.

Refs: https://huggingface.co/spaces/ggml-org/gguf-my-repo/discussions/186#68938de803e47d990aa087fb
Refs: https://github.com/pytorch/pytorch/issues/58734
 2025-08-07 05:31:48 +02:00
Reese Levine
5fd160bbd9
ggml: Add basic SET_ROWS support in WebGPU (#15137) 
* Begin work on set_rows

* Work on set rows

* Add error buffers for reporting unsupported SET_ROWS indices

* Remove extra comments
 2025-08-06 15:14:40 -07:00
rmatif
756cfea826
fix profiling crash (#15072) 2025-08-06 14:17:51 -07:00
lhez
e725a1a982
opencl: add swiglu_oai and add_id (#15121) 
* opencl: add `swiglu-oai`

* opencl: add `add_id`

* opencl: add missing `add_id.cl`
 2025-08-06 12:12:17 -07:00
Sachin Desai
3db4da56a5
chat : support Granite model reasoning and tool call (#14864) 2025-08-06 20:27:30 +02:00
Juk Armstrong
476aa3fd57
Fixed name -override-tensors to -override-tensor (#15129) 2025-08-06 17:28:48 +01:00
Diego Devesa
0d8831543c
ggml : fix fallback to CPU for ununsupported ops (#15118) 2025-08-06 14:37:35 +02:00
Sigbjørn Skjæret
65c797c4fa
chat : fix yandex chat template (#15116) 2025-08-06 13:26:49 +02:00
stevenkuang
25726898e8
chat : fix hunyuan auto-detection (#15114) 
Signed-off-by: stevenkuang <stevenkuang@tencent.com>
 2025-08-06 11:48:30 +02:00
Concedo
61c19fea56 fixed glm4 sop, lower regex max stacks (+2 squashed commit) 
Squashed commit:

[47e39ae5d] lower regex max stack again

[0a32ca232] lower regex max stack again
 2025-08-06 17:10:57 +08:00
Chenguang Li
2241453252
CANN: add support for ACL Graph (#15065) 
* feat(cann): add optional support for ACL Graph execution

This commit adds support for executing ggml computational graphs using
Huawei's ACL graph mode via the USE_CANN_GRAPH flag. The support can be
enabled at compile time using the CMake option:

    -DUSE_CANN_GRAPH=ON

By default, ACL graph execution is **disabled**, and the fallback path
uses node-by-node execution.

Key additions:
- CMake option  to toggle graph mode
- Graph capture and execution logic using
- Tensor property matching to determine whether graph update is required
- Safe fallback and logging if the environment variable LLAMA_SET_ROWS
  is unset or invalid

This prepares the backend for performance improvements in repetitive graph
execution scenarios on Ascend devices.

Signed-off-by: noemotiovon <757486878@qq.com>

* Fix review comments

Signed-off-by: noemotiovon <757486878@qq.com>

* remane USE_CANN_GRAPH to USE_ACL_GRAPH

Signed-off-by: noemotiovon <757486878@qq.com>

* fix typo

Signed-off-by: noemotiovon <757486878@qq.com>

---------

Signed-off-by: noemotiovon <757486878@qq.com>
 2025-08-06 14:12:42 +08:00
Concedo
34487d3c02 gpt oss harmony template 2025-08-06 11:39:40 +08:00
Concedo
6eea7b88d2 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	README.md
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
 2025-08-06 10:51:29 +08:00
Reese Levine
9515c6131a
ggml: WebGPU disable SET_ROWS for now (#15078) 
* Add paramater buffer pool, batching of submissions, refactor command building/submission

* Add header for linux builds

* Free staged parameter buffers at once

* Format with clang-format

* Fix thread-safe implementation

* Use device implicit synchronization

* Update workflow to use custom release

* Remove testing branch workflow

* Disable set_rows until it's implemented

* Fix potential issue around empty queue submission

* Try synchronous submission

* Try waiting on all futures explicitly

* Add debug

* Add more debug messages

* Work on getting ssh access for debugging

* Debug on failure

* Disable other tests

* Remove extra if

* Try more locking

* maybe passes?

* test

* Some cleanups

* Restore build file

* Remove extra testing branch ci
 2025-08-05 16:26:38 -07:00
Georgi Gerganov
fd1234cb46
llama : add gpt-oss (#15091) 
* oai moe

* compat with new checkpoint

* add attn sink impl

* add rope scaling yarn

* logits match with latest transformers code

* wip chat template

* rm trailing space

* use ggml_scale_bias

* rm redundant is_swa_all

* convert interleaved gate_up

* graph : fix activation function to match reference (#7)

* vocab : handle o200k_harmony special tokens

* ggml : add attention sinks support (#1)

* llama : add attn sinks

* ggml : add attn sinks

* cuda : add attn sinks

* vulkan : add support for sinks in softmax

remove unnecessary return

* ggml : add fused swiglu_oai op (#11)

* ggml : add fused swiglu_oai op

* Update ggml/src/ggml-cpu/ops.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* update CUDA impl

* cont : metal impl

* add vulkan impl

* test-backend-ops : more test cases, clean up

* llama : remove unfused impl

* remove extra lines

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: slaren <slarengh@gmail.com>

* repack mxfp4 upon conversion

* clean up a bit

* enable thinking

* add quick hack to render only some special tokens

* fix bf16 conversion

* remove vocab hack

* webui ok

* support chat parsing for gpt-oss

* fix webui

* direct mapping mxfp4, FINALLY

* force using mxfp4

* properly use lazy tensor

* ggml : add mxfp4

ggml : use e8m0 conversion instead of powf

Co-authored-by: Diego Devesa <slarengh@gmail.com>

change kvalues_mxfp4 table to match e2m1 (#6)

metal : remove quantization for now (not used)

cuda : fix disabled CUDA graphs due to ffn moe bias

vulkan : add support for mxfp4

cont : add cm2 dequant

* ggml : add ggml_add_id (#13)

* ggml : add ggml_add_id

* add cuda impl

* llama : add weight support check for add_id

* perf opt

* add vulkan impl

* rename cuda files

* add metal impl

* allow in-place ggml_add_id

* llama : keep biases on CPU with --cpu-moe

* llama : fix compile error

ggml-ci

* cuda : add fallback for __nv_cvt_e8m0_to_bf16raw

ggml-ci

* cleanup

ggml-ci

* sycl : fix supports_op for MXFP4

ggml-ci

* fix Unknown reasoning format

* ggml-cpu : fix AVX build

ggml-ci

* fix hip build

ggml-ci

* cuda : add mxfp4 dequantization support for cuBLAS

ggml-ci

* ggml-cpu : fix mxfp4 fallback definitions for some architectures

ggml-ci

* cuda : fix version required for __nv_cvt_e8m0_to_bf16raw

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: slaren <slarengh@gmail.com>
 2025-08-05 22:10:36 +03:00
Sigbjørn Skjæret
f324a3b715
chat : only remove double bos/eos if added (#15086) 
* only remove double bos/eos if added

* fix tests
 2025-08-05 20:43:36 +02:00
Georgi Gerganov
be42642581
readme : update hot topics (#15097) 2025-08-05 20:19:33 +03:00
Concedo
8bffbd9ce5 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	ggml/src/ggml-sycl/ggml-sycl.cpp
 2025-08-06 00:44:19 +08:00
Concedo
8323d8a2d7 try fix regex stack size issues 2025-08-06 00:44:05 +08:00