This website requires JavaScript.
Explore
Help
Sign In
tqcq
/
llama.cpp
Watch
0
Star
0
Fork
0
You've already forked llama.cpp
mirror of
https://github.com/ggml-org/llama.cpp.git
synced
2025-08-06 01:05:03 -04:00
Code
Issues
Packages
Projects
Releases
Wiki
Activity
Files
a05e2afcc241c1ecd38ec5cb4c579d90cdf3f918
llama.cpp
/
ggml
/
src
/
ggml-cuda
/
template-instances
History
Johannes Gäßler
69c487f4ed
CUDA: MMQ code deduplication + iquant support (
#8495
)
...
* CUDA: MMQ code deduplication + iquant support * 1 less parallel job for CI build
2024-07-20 22:25:26 +02:00
..
fattn-vec-f16-instance-hs64-f16-f16.cu
…
fattn-vec-f16-instance-hs64-f16-q4_0.cu
…
fattn-vec-f16-instance-hs64-f16-q4_1.cu
…
fattn-vec-f16-instance-hs64-f16-q5_0.cu
…
fattn-vec-f16-instance-hs64-f16-q5_1.cu
…
fattn-vec-f16-instance-hs64-f16-q8_0.cu
…
fattn-vec-f16-instance-hs128-f16-f16.cu
…
fattn-vec-f16-instance-hs128-f16-q4_0.cu
…
fattn-vec-f16-instance-hs128-f16-q4_1.cu
…
fattn-vec-f16-instance-hs128-f16-q5_0.cu
…
fattn-vec-f16-instance-hs128-f16-q5_1.cu
…
fattn-vec-f16-instance-hs128-f16-q8_0.cu
…
fattn-vec-f16-instance-hs128-q4_0-f16.cu
…
fattn-vec-f16-instance-hs128-q4_0-q4_0.cu
…
fattn-vec-f16-instance-hs128-q4_0-q4_1.cu
…
fattn-vec-f16-instance-hs128-q4_0-q5_0.cu
…
fattn-vec-f16-instance-hs128-q4_0-q5_1.cu
…
fattn-vec-f16-instance-hs128-q4_0-q8_0.cu
…
fattn-vec-f16-instance-hs128-q4_1-f16.cu
…
fattn-vec-f16-instance-hs128-q4_1-q4_0.cu
…
fattn-vec-f16-instance-hs128-q4_1-q4_1.cu
…
fattn-vec-f16-instance-hs128-q4_1-q5_0.cu
…
fattn-vec-f16-instance-hs128-q4_1-q5_1.cu
…
fattn-vec-f16-instance-hs128-q4_1-q8_0.cu
…
fattn-vec-f16-instance-hs128-q5_0-f16.cu
…
fattn-vec-f16-instance-hs128-q5_0-q4_0.cu
…
fattn-vec-f16-instance-hs128-q5_0-q4_1.cu
…
fattn-vec-f16-instance-hs128-q5_0-q5_0.cu
…
fattn-vec-f16-instance-hs128-q5_0-q5_1.cu
…
fattn-vec-f16-instance-hs128-q5_0-q8_0.cu
…
fattn-vec-f16-instance-hs128-q5_1-f16.cu
…
fattn-vec-f16-instance-hs128-q5_1-q4_0.cu
…
fattn-vec-f16-instance-hs128-q5_1-q4_1.cu
…
fattn-vec-f16-instance-hs128-q5_1-q5_0.cu
…
fattn-vec-f16-instance-hs128-q5_1-q5_1.cu
…
fattn-vec-f16-instance-hs128-q5_1-q8_0.cu
…
fattn-vec-f16-instance-hs128-q8_0-f16.cu
…
fattn-vec-f16-instance-hs128-q8_0-q4_0.cu
…
fattn-vec-f16-instance-hs128-q8_0-q4_1.cu
…
fattn-vec-f16-instance-hs128-q8_0-q5_0.cu
…
fattn-vec-f16-instance-hs128-q8_0-q5_1.cu
…
fattn-vec-f16-instance-hs128-q8_0-q8_0.cu
…
fattn-vec-f16-instance-hs256-f16-f16.cu
…
fattn-vec-f32-instance-hs64-f16-f16.cu
…
fattn-vec-f32-instance-hs64-f16-q4_0.cu
…
fattn-vec-f32-instance-hs64-f16-q4_1.cu
…
fattn-vec-f32-instance-hs64-f16-q5_0.cu
…
fattn-vec-f32-instance-hs64-f16-q5_1.cu
…
fattn-vec-f32-instance-hs64-f16-q8_0.cu
…
fattn-vec-f32-instance-hs128-f16-f16.cu
…
fattn-vec-f32-instance-hs128-f16-q4_0.cu
…
fattn-vec-f32-instance-hs128-f16-q4_1.cu
…
fattn-vec-f32-instance-hs128-f16-q5_0.cu
…
fattn-vec-f32-instance-hs128-f16-q5_1.cu
…
fattn-vec-f32-instance-hs128-f16-q8_0.cu
…
fattn-vec-f32-instance-hs128-q4_0-f16.cu
…
fattn-vec-f32-instance-hs128-q4_0-q4_0.cu
…
fattn-vec-f32-instance-hs128-q4_0-q4_1.cu
…
fattn-vec-f32-instance-hs128-q4_0-q5_0.cu
…
fattn-vec-f32-instance-hs128-q4_0-q5_1.cu
…
fattn-vec-f32-instance-hs128-q4_0-q8_0.cu
…
fattn-vec-f32-instance-hs128-q4_1-f16.cu
…
fattn-vec-f32-instance-hs128-q4_1-q4_0.cu
…
fattn-vec-f32-instance-hs128-q4_1-q4_1.cu
…
fattn-vec-f32-instance-hs128-q4_1-q5_0.cu
…
fattn-vec-f32-instance-hs128-q4_1-q5_1.cu
…
fattn-vec-f32-instance-hs128-q4_1-q8_0.cu
…
fattn-vec-f32-instance-hs128-q5_0-f16.cu
…
fattn-vec-f32-instance-hs128-q5_0-q4_0.cu
…
fattn-vec-f32-instance-hs128-q5_0-q4_1.cu
…
fattn-vec-f32-instance-hs128-q5_0-q5_0.cu
…
fattn-vec-f32-instance-hs128-q5_0-q5_1.cu
…
fattn-vec-f32-instance-hs128-q5_0-q8_0.cu
…
fattn-vec-f32-instance-hs128-q5_1-f16.cu
…
fattn-vec-f32-instance-hs128-q5_1-q4_0.cu
…
fattn-vec-f32-instance-hs128-q5_1-q4_1.cu
…
fattn-vec-f32-instance-hs128-q5_1-q5_0.cu
…
fattn-vec-f32-instance-hs128-q5_1-q5_1.cu
…
fattn-vec-f32-instance-hs128-q5_1-q8_0.cu
…
fattn-vec-f32-instance-hs128-q8_0-f16.cu
…
fattn-vec-f32-instance-hs128-q8_0-q4_0.cu
…
fattn-vec-f32-instance-hs128-q8_0-q4_1.cu
…
fattn-vec-f32-instance-hs128-q8_0-q5_0.cu
…
fattn-vec-f32-instance-hs128-q8_0-q5_1.cu
…
fattn-vec-f32-instance-hs128-q8_0-q8_0.cu
…
fattn-vec-f32-instance-hs256-f16-f16.cu
…
fattn-wmma-f16-instance-kqfloat-cpb16.cu
…
fattn-wmma-f16-instance-kqfloat-cpb32.cu
…
fattn-wmma-f16-instance-kqhalf-cpb8.cu
…
fattn-wmma-f16-instance-kqhalf-cpb16.cu
…
fattn-wmma-f16-instance-kqhalf-cpb32.cu
…
generate_cu_files.py
CUDA: MMQ code deduplication + iquant support (
#8495
)
2024-07-20 22:25:26 +02:00
mmq-instance-iq1_s.cu
CUDA: MMQ code deduplication + iquant support (
#8495
)
2024-07-20 22:25:26 +02:00
mmq-instance-iq2_s.cu
CUDA: MMQ code deduplication + iquant support (
#8495
)
2024-07-20 22:25:26 +02:00
mmq-instance-iq2_xs.cu
CUDA: MMQ code deduplication + iquant support (
#8495
)
2024-07-20 22:25:26 +02:00
mmq-instance-iq2_xxs.cu
CUDA: MMQ code deduplication + iquant support (
#8495
)
2024-07-20 22:25:26 +02:00
mmq-instance-iq3_s.cu
CUDA: MMQ code deduplication + iquant support (
#8495
)
2024-07-20 22:25:26 +02:00
mmq-instance-iq3_xxs.cu
CUDA: MMQ code deduplication + iquant support (
#8495
)
2024-07-20 22:25:26 +02:00
mmq-instance-iq4_nl.cu
…
mmq-instance-iq4_xs.cu
…
mmq-instance-q2_k.cu
…
mmq-instance-q3_k.cu
…
mmq-instance-q4_0.cu
…
mmq-instance-q4_1.cu
…
mmq-instance-q4_k.cu
…
mmq-instance-q5_0.cu
…
mmq-instance-q5_1.cu
…
mmq-instance-q5_k.cu
…
mmq-instance-q6_k.cu
…
mmq-instance-q8_0.cu
…