Skip to content

Releases: struct/llama.cpp

b5990

25 Jul 13:52
e2b7621

Choose a tag to compare

ggml : remove invalid portPos specifiers from dot files (#14838)

Neither "g" nor "x" are valid portPos specifiers per the official
[graphviz documents](https://graphviz.org/docs/attr-types/portPos/):

> If a compass point is used, it must have the form "n","ne","e","se","s","sw","w","nw","c","_".

I tested locally for it to fall back to default portPos specifier if an
invalid portPos is specified. As a consequence, we can remove associated
code.

b5985

25 Jul 02:58
3f4fc97

Choose a tag to compare

musa: upgrade musa sdk to rc4.2.0 (#14498)

* musa: apply mublas API changes

Signed-off-by: Xiaodong Ye <[email protected]>

* musa: update musa version to 4.2.0

Signed-off-by: Xiaodong Ye <[email protected]>

* musa: restore MUSA graph settings in CMakeLists.txt

Signed-off-by: Xiaodong Ye <[email protected]>

* musa: disable mudnnMemcpyAsync by default

Signed-off-by: Xiaodong Ye <[email protected]>

* musa: switch back to non-mudnn images

Signed-off-by: Xiaodong Ye <[email protected]>

* minor changes

Signed-off-by: Xiaodong Ye <[email protected]>

* musa: restore rc in docker image tag

Signed-off-by: Xiaodong Ye <[email protected]>

---------

Signed-off-by: Xiaodong Ye <[email protected]>

b5971

23 Jul 13:16
221c0e0

Choose a tag to compare

ci : correct label refactor->refactoring (#14832)

b5964

22 Jul 17:59
acd6cb1

Choose a tag to compare

ggml : model card yaml tab->2xspace (#14819)

b5955

21 Jul 23:30
38d3af1

Choose a tag to compare

opencl: fix `im2col` when `KW!=KH` (#14803)

b5884

12 Jul 23:28
c31e606

Choose a tag to compare

tests : cover lfm2 cases in test_ssm_conv (#14651)

b5849

08 Jul 23:14
6efcd65

Choose a tag to compare

vulkan: optimize flash attention split_k_reduce (#14554)

* vulkan: allow FA split_k with smaller KV values

* vulkan: spread split_k_reduce work across more threads

k_num can get rather large. Use the whole workgroup to reduce the M/L values.

Launch a thread for each element in the HSV dimension of the output. Helps a
lot for large HSV (like deepseek).