Skip to content

Releases: githubcto/llama.cpp

SD3GGUF-b3986-89406a9

27 Oct 15:10
89406a9
Compare
Choose a tag to compare

llama-quantize.exe for SD SDXL SD3 FLUX SD3.5
GGUF lcpp_sd3.patch patched
GPU_TARGETS="gfx1100;gfx1101;gfx1102;gfx1030;gfx906"

llama-quantize.exe for SD SDXL SD3 FLUX qt-b3923-a58a0a4

15 Oct 11:17
a58a0a4
Compare
Choose a tag to compare

llama-quantize.exe for SD SDXL SD3 FLUX
GGUF lcpp.patch hand patched

b3920

15 Oct 02:47
33559d8
Compare
Choose a tag to compare

add ROCm6 gfx1100;gfx1101;gfx1102;gfx1030;gfx906

b3917

14 Oct 08:02
a89f75e
Compare
Choose a tag to compare
server : handle "logprobs" field with false value (#9871)

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