Skip to content

Releases: fairydreaming/llama.cpp

b4255

03 Dec 20:55
cc98896
Compare
Choose a tag to compare
vulkan: optimize and reenable split_k (#10637)

Use vector loads when possible in mul_mat_split_k_reduce. Use split_k
when there aren't enough workgroups to fill the shaders.

b4219

29 Nov 13:17
266b851
Compare
Choose a tag to compare
sycl : Reroute permuted mul_mats through oneMKL (#10408)

This PR fixes the failing MUL_MAT tests for the sycl backend.

b3605

19 Aug 19:12
cfac111
Compare
Choose a tag to compare
cann: add doc for cann backend (#8867)

Co-authored-by: xuedinge233 <[email protected]>
Co-authored-by: hipudding <[email protected]>

b3357

09 Jul 20:54
fd560fe
Compare
Choose a tag to compare
Update README.md to fix broken link to docs (#8399)

Update the "Performance troubleshooting" doc link to be correct - the file was moved into a dir called 'development'

b3212

24 Jun 07:50
8cb508d
Compare
Choose a tag to compare
disable publishing the full-rocm docker image (#8083)

b3197

21 Jun 12:12
557b653
Compare
Choose a tag to compare
vulkan: detect multiple devices by deviceUUID instead of deviceID (#8…

b3190

20 Jun 18:39
abd894a
Compare
Choose a tag to compare
common: fix warning (#8036)

* common: fix warning

* Update common/common.cpp

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

---------

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

b3145

13 Jun 20:16
172c825
Compare
Choose a tag to compare
rpc : fix ggml_backend_rpc_supports_buft() (#7918)

b2963

22 May 11:00
95fb0ae
Compare
Choose a tag to compare
CUDA: remove incorrect precision check (#7454)