Skip to content

Releases: ngxson/llama.cpp

b4682

10 Feb 17:48
0893e01
Compare
Choose a tag to compare
server : correct signal handler (#11795)

b4681

10 Feb 10:18
d7b31a9
Compare
Choose a tag to compare
sync: minja (https://github.com/google/minja/commit/a72057e5190de2c61…

b4679

10 Feb 06:54
c2a67ef
Compare
Choose a tag to compare
vulkan: Make Vulkan optional at runtime (#11493). (#11494)

Co-authored-by: Jeff Bolz <[email protected]>

b4678

10 Feb 06:42
b044a0f
Compare
Choose a tag to compare
vulkan: add environment variable GGML_VK_PREFER_HOST_MEMORY to avoid …

b4677

09 Feb 11:10
19d3c82
Compare
Choose a tag to compare
There's a better way of clearing lines (#11756)

Use the ANSI escape code for clearing a line.

Signed-off-by: Eric Curtin <[email protected]>

b4676

09 Feb 08:19
98f6b0f
Compare
Choose a tag to compare
vulkan: account for lookup tables when checking shared memory size (#…

b4675

08 Feb 21:30
55ac8c7
Compare
Choose a tag to compare
server : (webui) revamp Settings dialog, add Pyodide interpreter (#11…

b4674

08 Feb 19:45
e6e6583
Compare
Choose a tag to compare
server : (webui) increase edit textarea size (#11763)

b4667

07 Feb 15:18
d2fe216
Compare
Choose a tag to compare
Make logging more verbose (#11714)

Debugged an issue with a user who was on a read-only filesystem.

Signed-off-by: Eric Curtin <[email protected]>

b4666

07 Feb 14:55
ed926d8
Compare
Choose a tag to compare
llama : fix defrag logic (#11707)

* llama : fix defrag logic

ggml-ci

* cont : better logic

ggml-ci

* cont : clamp fragmentation to 0.0

ggml-ci