Skip to content

Releases: 3Simplex/llama.cpp

b3531

06 Aug 14:04
efda90c
Compare
Choose a tag to compare
[Vulkan] Fix compilation of `vulkan-shaders-gen` on w64devkit after `…

b3504

02 Aug 13:01
e09a800
Compare
Choose a tag to compare
cann: Fix ggml_cann_im2col for 1D im2col (#8819)

* fix ggml_cann_im2col for 1D im2col

* fix build warning

b3501

01 Aug 19:03
b7a08fd
Compare
Choose a tag to compare
Build: Only include execinfo.h on linux systems that support it (#8783)

* Only enable backtrace on GLIBC linux systems

* fix missing file from copy

* use glibc macro instead of defining a custom one

b3494

31 Jul 13:13
268c566
Compare
Choose a tag to compare
nix: cuda: rely on propagatedBuildInputs (#8772)

Listing individual outputs no longer necessary to reduce the runtime closure size after https://github.com/NixOS/nixpkgs/pull/323056.

b3472

27 Jul 14:12
b5e9546
Compare
Choose a tag to compare
llama : add support for llama 3.1 rope scaling factors (#8676)

* Add llama 3.1 rope scaling factors to llama conversion and inference

This commit generates the rope factors on conversion and adds them to the resulting model as a tensor. At inference time, these factors are passed to the `ggml_rope_ext` rope oepration, improving results for context windows above 8192

* Update convert_hf_to_gguf.py

Co-authored-by: compilade <[email protected]>

* address comments

* address comments

* Update src/llama.cpp

Co-authored-by: compilade <[email protected]>

* Update convert_hf_to_gguf.py

Co-authored-by: compilade <[email protected]>

---------

Co-authored-by: compilade <[email protected]>

b3468

27 Jul 05:16
2b1f616
Compare
Choose a tag to compare
ggml : reduce hash table reset cost (#8698)

* ggml : reduce hash table reset cost

* fix unreachable code warnings after GGML_ASSERT(false)

* GGML_ASSERT(false) -> GGML_ABORT("fatal error")

* GGML_ABORT use format string

b3467

26 Jul 13:36
01245f5
Compare
Choose a tag to compare
llama : fix order of parameters (#8706)

usage of `aclrtGetMemInfo` is correct:

https://www.hiascend.com/doc_center/source/zh/canncommercial/63RC2/inferapplicationdev/aclcppdevg/aclcppdevg_03_0103.html

Co-authored-by: Judd <[email protected]>

b3463

25 Jul 18:40
4226a8d
Compare
Choose a tag to compare
llama : fix build + fix fabs compile warnings (#8683)

ggml-ci

b3460

25 Jul 12:57
ed67bcb
Compare
Choose a tag to compare
[SYCL] fix multi-gpu issue on sycl (#8554)



---------

Signed-off-by: Chen Xi <[email protected]>
Co-authored-by: Meng, Hengyu <[email protected]>

b3455

24 Jul 22:31
68504f0
Compare
Choose a tag to compare
readme : update games list (#8673)

Added link to game I made that depends on llama