 eiery
|
f2d1c47294
cmake should link openblas properly with -lopenblas like how it's done in the makefile (#839)
|
2 years ago |
 lon
|
317fb12fbd
Add new binaries to flake.nix (#847)
|
2 years ago |
 unbounded
|
62cfc54f77
Add quantize-stats command for testing quantization (#728)
|
2 years ago |
 bhubbb
|
698f7b5d63
make : add libllama.so target for llama-cpp-python (#797)
|
2 years ago |
 iacore
|
c1950c3431
zig : don't link examples/common.cpp for non-example (#814)
|
2 years ago |
 Ivan Stepanov
|
4953e9007f
llama : always sort logits before nucleus sampling (#812)
|
2 years ago |
 Sergey Alirzaev
|
cc9cee8e9e
Do not crash when it has nothing to say. (#796)
|
2 years ago |
 Pavol Rusnak
|
d2beca95dc
Make docker instructions more explicit (#785)
|
2 years ago |
 Georgi Gerganov
|
eeaa7b0492
ggml : multi-thread ggml_rope() (~3-4 times faster on M1) (#781)
|
2 years ago |
|
Georgi Gerganov
|
986b6ce9f9
ggml, llama : avoid heavy V transpose + improvements (#775)
|
2 years ago |
|
Georgi Gerganov
|
3416298929
Update README.md
|
2 years ago |
|
Ivan Stepanov
|
5a8c4f6240
llama : define non-positive top_k; top_k range check (#779)
|
2 years ago |
 at8u
|
ff05d05c96
miku.sh : add executable bit (#780)
|
2 years ago |
|
Georgi Gerganov
|
62b3e81aae
media : add logos and banners
|
2 years ago |
|
Georgi Gerganov
|
8d10406d6e
readme : change logo + add bindings + add uis + add wiki
|
2 years ago |
|
iacore
|
ed1c214e66
zig : add build.zig (#773)
|
2 years ago |
|
Ivan Stepanov
|
0c44427df1
make : missing host optimizations in CXXFLAGS (#763)
|
2 years ago |
 Adithya Balaji
|
594cc95fab
readme : update with CMake and windows example (#748)
|
2 years ago |
|
at8u
|
88ed5761b8
examples : add Miku.sh (#724)
|
2 years ago |
 Andrew Duffy
|
58c438cf7d
Add Accelerate/BLAS when using Swift (#765)
|
2 years ago |
 mgroeber9110
|
53dbba7695
Windows: reactive sigint handler after each Ctrl-C (#736)
|
2 years ago |
 SebastianApel
|
437e77855a
10+% performance improvement of ggml_vec_dot_q4_0 on AVX2 (#654)
|
2 years ago |
|
Ivan Stepanov
|
cd7fa95690
Define non-positive temperature behavior (#720)
|
2 years ago |
 bsilvereagle
|
a0c0516416
Remove torch GPU dependencies from the Docker.full image (#665)
|
2 years ago |
 Thatcher Chamberlin
|
d8d4e865cd
Add a missing step to the gpt4all instructions (#690)
|
2 years ago |
 Christian Falch
|
e986f94829
Added api for getting/setting the kv_cache (#685)
|
2 years ago |
 Marian Cepok
|
c0bb1d3ce2
ggml : change ne to int64_t (#626)
|
2 years ago |
 Leonardo Neumann
|
6e7801d08d
examples : add gpt4all script (#658)
|
2 years ago |
 Stephan Walter
|
81040f10aa
llama : do not allocate KV cache for "vocab_only == true" (#682)
|
2 years ago |
 Fabian
|
c4f89d8d73
make : use -march=native -mtune=native on x86 (#609)
|
2 years ago |
