vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-13 02:19:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
6004 commits 3 branches 196 tags 389 MiB
Commit graph

6004 commits

This branch
This branch
All branches
Author SHA1 Message Date
Concedo
06d9068c97 copy the metal file to root dir as well 2024-07-02 23:51:21 +08:00
Faisal Zaghloul
968967376d
Add JAIS model(s) (#8118) 
* Add `JAIS` model(s)

* cleanup

* address review comments

* remove hack

* un-hardcode max-alibi-bias

* minor tweaks

---------

Co-authored-by: fmz <quic_fzaghlou@quic.com>
 2024-07-02 16:36:00 +02:00
Concedo
0fc18d2d82 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/nix/package.nix
#	CMakePresets.json
#	README.md
#	flake.lock
#	ggml/src/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
 2024-07-02 21:05:45 +08:00
Concedo
82202aebda updated lite, add gemma 2 template 2024-07-02 21:02:52 +08:00
Daniel Bevenius
023b8807e1
convert-hf : print output file name when completed (#8181) 
* convert-hf : print output file name when completed

This commit adds the output file name to the log message when the
conversion is completed.

The motivation for this change is that when `--outfile` option is not
specified it migth not be obvious where the output file is written.

With this change the output of running the script will be something like
the following:
```console
INFO:hf-to-gguf:Model successfully exported to models/gemma-2-9b-it.gguf.
```

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* squash! convert-hf : print output file name when completed

Updates the output of to support printing the directory if the output is
split into multiple files. Also the output file name is now retrieved
from the model_instance object.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* squash! convert-hf : print output file name when completed

Use parent attribute of Path object and string interpolation.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* squash! convert-hf : print output file name when completed

Use os.sep instead of hardcoding the path separator.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

---------

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
 2024-07-02 09:40:49 +03:00
slaren
0e0590adab
cuda : update supports_op for matrix multiplication (#8245) 2024-07-02 09:39:38 +03:00
luoyu-intel
a9f3b10215
[SYCL] Fix win build conflict of math library (#8230) 
* fix win build conflict of math library

* fix the condition: !(win32 & SYCL)

* revert warp_size=16
 2024-07-02 12:50:07 +08:00
luoyu-intel
d08c20edde
[SYCL] Fix the sub group size of Intel (#8106) 
* use warp_size macro for all sycl kernels

* fix mask of permute_sub_group_by_xor

* fix rms_norm with correct warp number

* fix rms_norm_f32/group_norm_f32

* move norm to norm.cpp file

* fix quantize bug

* fix mmvq's batch size
 2024-07-02 10:16:00 +08:00
Xuan Son Nguyen
5fac350b9c
Fix gemma2 tokenizer convert (#8244) 
* fix gemma2 tokenizer convert

* remove scores

* improve code, fix new line issue
 2024-07-02 01:07:23 +02:00
Johannes Gäßler
cb5fad4c6c
CUDA: refactor and optimize IQ MMVQ (#8215) 
* CUDA: refactor and optimize IQ MMVQ

* uint -> uint32_t

* __dp4a -> ggml_cuda_dp4a

* remove MIN_CC_DP4A checks

* change default

* try CI fix
 2024-07-01 20:39:06 +02:00
Mateusz Charytoniuk
dae57a1ebc
readme: add Paddler to the list of projects (#8239) 2024-07-01 20:13:22 +03:00
Xuan Son Nguyen
49122a873f
gemma2: add sliding window mask (#8227) 
* gemma2: add sliding window mask

* fix data_swa uninitialized

* better naming

* add co-author

Co-authored-by: Arlo Phoenix <arlo-phoenix@users.noreply.github.com>

* replace list with single tensor

* update

* llama : minor styling

* convert : add sanity check for query_pre_attn_scalar

* fix small typo in README

---------

Co-authored-by: Arlo Phoenix <arlo-phoenix@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2024-07-01 18:48:34 +02:00
Roni
0ddeff1023
readme : update tool list (#8209) 
* Added gppm to Tool list in README

* Update README.md

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2024-07-01 15:48:16 +03:00
Michael Francis
3840b6f593
nix : enable curl (#8043) 
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2024-07-01 14:47:04 +03:00
Georgi Gerganov
257f8e41e2
nix : remove OpenCL remnants (#8235) 
* nix : remove OpenCL remnants

* minor : remove parentheses
 2024-07-01 14:46:18 +03:00
iacore
694c59cb42
Document BERT support. (#8205) 
* Update README.md

document BERT support

* Update README.md
 2024-07-01 13:40:58 +02:00
zhentaoyu
197fe6c1d7
[SYCL] Update SYCL-Rope op and Refactor (#8157) 
* align with rope.cu and move sycl-op to a single file
 2024-07-01 19:39:06 +08:00
Georgi Gerganov
d0a7145ba9
flake.lock: Update (#8218) 2024-06-30 16:09:34 -07:00
Xuan Son Nguyen
9ef0780062
Fix new line issue with chat template, disable template when in-prefix/suffix is set (#8203) 
* preserve new line llama_chat_format_single

* disable chat template if in-prefix/suffix is set

* remove redundant change
 2024-06-30 20:27:13 +02:00
bebopkim
7499a6bd4b
Resolve make: *** No rule to make target ggml-metal.m', needed by ggml-metal.o'. Stop error on macOS Metal (#957) 2024-06-30 16:05:03 +08:00
Concedo
b1f9c97a0b Merge branch 'upstream' into concedo_experimental 2024-06-30 11:50:40 +08:00
Concedo
8a07ce306a edit sampler order warning 2024-06-30 11:46:09 +08:00
Andrei
1c5eba6f8e
llama: Add attention and final logit soft-capping, update scaling factor to Gemma2 (#8197) 
* Add attention and final logit softcapping.

* fix

* Add custom add_ functions

* Disable flash attention for Gemma2

* Update src/llama.cpp

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

* Add default value for attention and final logit softcap value

* Add custom kq scaling from Gemma2Attention

* Remove custom pre attention scaling and use computed value instead.

---------

Co-authored-by: slaren <slarengh@gmail.com>
 2024-06-29 23:44:08 -04:00
Concedo
18df56b8cf add tensor split gui input for vulkan 2024-06-30 11:16:48 +08:00
Concedo
02f92f6ecc Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/full-rocm.Dockerfile
#	.devops/llama-cli-cuda.Dockerfile
#	.devops/llama-cli-rocm.Dockerfile
#	.devops/llama-cli-vulkan.Dockerfile
#	.devops/llama-cpp-cuda.srpm.spec
#	.devops/llama-server-cuda.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.devops/llama-server-vulkan.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	examples/llama.android/llama/src/main/cpp/CMakeLists.txt
#	flake.lock
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	grammars/README.md
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.last
#	tests/test-chat-template.cpp
#	tests/test-grammar-integration.cpp
#	tests/test-json-schema-to-grammar.cpp
 2024-06-30 10:59:42 +08:00
henk717
8421243c6d
Chat Adapters (#956) 
* Give the CI builds a recognizable AVX1 name

* Chat Adapters
 2024-06-30 10:28:43 +08:00
Concedo
d120c55e12 try to fix build errors (+1 squashed commits) 
Squashed commits:

[27c28292] try fix build errors
 2024-06-29 23:11:00 +08:00
Concedo
9c10486204 merge the file structure refactor, testing 2024-06-29 12:14:38 +08:00
Nexesenex
a5a32b9179
Add Cuda Graphs in CMakeList (#947) 
original LCPP PR 3242 by Slaren
 2024-06-29 10:10:51 +08:00
Xuan Son Nguyen
72272b83a3
fix code typo in llama-cli (#8198) 2024-06-29 00:14:20 +02:00
Olivier Chafik
8748d8ac6f
json: attempt to skip slow tests when running under emulator (#8189) 2024-06-28 18:02:05 +01:00
Concedo
2857fb52ba remove contribute template 2024-06-28 23:47:03 +08:00
Nexesenex
1203a56f6b
Add Cublas12 dlls to .gitignore (#946) 2024-06-28 23:41:44 +08:00
Xuan Son Nguyen
26a39bbd6b
Add MiniCPM, Deepseek V2 chat template + clean up llama_chat_apply_template_internal (#8172) 
* tmp_contains

* minicpm chat template

* add DeepSeek Lite template

* change deepseek-lite to deepseek2

* correct code comment

* correct code from master branch
 2024-06-28 15:11:44 +02:00
Sigbjørn Skjæret
38373cfbab
Add SPM infill support (#8016) 
* add --spm-infill option

* support --spm-infill

* support --spm-infill
 2024-06-28 12:53:43 +02:00
slaren
b851b3fba0
cmake : allow user to override default options (#8178) 2024-06-28 12:37:45 +02:00
Concedo
5e671c2162 ignore utf decode errors 2024-06-28 16:39:48 +08:00
Olivier Chafik
139cc621e9
json: restore default additionalProperties to false, fix some pattern escapes (#8180) 
* json: expand ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS charset

* json: revert default of additionalProperties to false

* Update README.md
 2024-06-28 09:26:45 +01:00
Concedo
3e6a9673ef add runpod to readme 2024-06-28 14:47:11 +08:00
pculliton
e57dc62057
llama: Add support for Gemma2ForCausalLM (#8156) 
* Inference support for Gemma 2 model family

* Update convert-hf-to-gguf.py, constants, and tensor mappings

* cleanup

* format fix

* Fix special token vocab bug

* Don't add space prefix

* fix deleted lines

* Update src/llama.cpp

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

* Add model type names

* Add control vector

* Fix model type identification

---------

Co-authored-by: Andrei Betlen <abetlen@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
 2024-06-27 21:00:43 -07:00
Xuan Son Nguyen
a27aa50ab7
Add missing items in makefile (#8177) 2024-06-28 02:19:11 +02:00
Olivier Chafik
cb0b06a8a6
json: update grammars/README w/ examples & note about additionalProperties (#8132) 
* json: update grammars/README

* mention broken prefixItems

* add mention to llama-gbnf-validator

* json: explicit type: object for nested items object in cli example
 2024-06-27 22:08:42 +01:00
loonerin
558f44bf83
CI: fix release build (Ubuntu+Mac) (#8170) 
* CI: fix release build (Ubuntu)

PR #8006 changes defaults to build shared libs. However, CI for releases
expects static builds.

* CI: fix release build (Mac)

---------

Co-authored-by: loonerin <loonerin@users.noreply.github.com>
 2024-06-27 21:01:23 +02:00
slaren
8172ee9da9
cmake : fix deprecated option names not working (#8171) 
* cmake : fix deprecated option names not working

* remove LlAMA_OPENMP
 2024-06-27 20:04:39 +02:00
Xuan Son Nguyen
16791b8f0b
Add chatml fallback for cpp llama_chat_apply_template (#8160) 
* add chatml fallback for cpp `llama_chat_apply_template`

* remove redundant code
 2024-06-27 18:14:19 +02:00
Georgi Gerganov
ab3679112d
flake.lock: Update (#8071) 
Flake lock file updates:

• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/e9ee548d90ff586a6471b4ae80ae9cfcbceb3420?narHash=sha256-4Zu0RYRcAY/VWuu6awwq4opuiD//ahpc2aFHg2CWqFY%3D' (2024-06-13)
  → 'github:NixOS/nixpkgs/d603719ec6e294f034936c0d0dc06f689d91b6c3?narHash=sha256-k3JqJrkdoYwE3fHE6xGDY676AYmyh4U2Zw%2B0Bwe5DLU%3D' (2024-06-20)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Philip Taron <philip.taron@gmail.com>
 2024-06-27 08:37:29 -07:00
jukofyork
97877eb10b
Control vector loading fixes (#8137) 
* Fixed leak in llama_control_vector_load_one() and allow llama_control_vector_load() to grow

* refactored `llama_control_vector_load_one()`

* allow multiple directions for same layer in same file

* llama_control_vector_load_one() and llama_control_vector_load() now break on error

* removed unnecessary ggml_free() call
 2024-06-27 16:48:07 +02:00
Raj Hammeer Singh Hada
387952651a
Delete examples/llama.android/llama/CMakeLists.txt (#8165) 
* Delete examples/llama.android/llama/CMakeLists.txt

https://github.com/ggerganov/llama.cpp/pull/8145#issuecomment-2194534244

This file is not being used for building on Android. `llama.cpp/examples/llama.android/llama/src/main/cpp/CMakeLists.txt` is being used instead.

* Update CMakeLists.txt

Pick local llama.cpp files instead of fetching content from git
 2024-06-27 16:39:29 +02:00
Sigbjørn Skjæret
6030c61281
Add Qwen2MoE 57B-A14B model identifier (#8158) 
* Add Qwen2MoE 57B-A14B

* Add Qwen2MoE 57B-A14B
 2024-06-27 16:27:41 +02:00
Johannes Gäßler
85a267daaa
CUDA: fix MMQ stream-k for --split-mode row (#8167) 2024-06-27 16:26:05 +02:00