Skip to content

Tags: ggml-org/llama.cpp

Tags

b4856

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
ggml-backend : make path_str compatible with C++20 (#12269)

b4855

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
server : infill gen ends on new line (#12254)

b4854

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
ggml : skip intermediate .air file when compiling .metallib (#12247)

This commit updates the compilation of default.metallib to skip the
intermediate .air (Apple Intermediate Representation) file.

The motivation for this change is to simplify the custom command a
little and avoid generating and then removing the .air file.

b4853

sync : ggml

ggml-ci

b4851

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
ggml-cpu: faster AVX2 variant for IQ1_M (#12216)

b4849

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
server : Log original chat template parsing error (#12233)

b4848

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
sync: minja - support QwQ-32B (#12235)

google/minja@8a76f78

b4847

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
metal : simplify kernel arguments using a struct (#3229) (#12194)

* metal : refactor im2col parameters into a struct

* metal: Change im2col offset types from int32_t to uint64_t to support larger memory offsets

* metal : refactor sum_rows parameters into a struct

* metal : refactor soft_max parameters into a struct

* metal : refactor diag_mask_inf parameters into a struct

* metal : refactor ssm_conv parameters into a struct

* metal : refactor ssm_scan parameters into a struct

* metal : refactor get_rows parameters into a struct

* metal : refactor group_norm parameters into a struct

* metal : refactor conv_transpose_1d parameters into a struct

* metal : refactor upscale parameters into a struct

* metal : refactor pad parameters into a struct

* metal : refactor pad_reflect_1d parameters into a struct

* metal : refactor arange parameters into a struct

* metal : refactor timestep_embedding parameters into a struct

* metal : refactor argsort parameters into a struct

* metal : refactor leaky_relu parameters into a struct

* metal : refactor pool_2d parameters into a struct

* metal : fix trailing whitespace

---------

Co-authored-by: alexju <alexju@tencent.com>

b4846

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
HIP: fix rocWMMA build flags under Windows (#12230)

b4837

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
HIP/CUDA: set the paramerter value in maintain_cuda_graph instead of …

…replaceing it. (#12209)

This avoids conflict with internal cuda/hip runtimes memory managment behavior.