8 Commits (bb0600c7da2d21937e416438254ff127c00b65bd)

Author SHA1 Message Date
Georgi Gerganov c80e2a8f2a
Revert "10% performance boost on ARM"
2 years ago
Georgi Gerganov 54a0e66ea0
Check for vdotq_s32 availability
2 years ago
Georgi Gerganov 543c57e991
Ammend to previous commit - forgot to update non-QRDMX branch
2 years ago
Georgi Gerganov 113a9e83eb
10% performance boost on ARM
2 years ago
Sebastián A eb062bb012
Windows fixes (#31)
2 years ago
Georgi Gerganov f1eaff4721 Add AVX2 support for x86 architectures thanks to @Const-me !
2 years ago
Georgi Gerganov 007a8f6f45
Support all LLaMA models + change Q4_0 quantization storage
2 years ago
Georgi Gerganov 26c0846629
Initial release
2 years ago