- 20 Sep, 2023 13 commits
-
-
Casper Hansen authored
-
Casper authored
-
Casper authored
-
Casper authored
-
Casper authored
-
Casper authored
Support kv_heads
-
Casper authored
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper authored
2x faster context processing with GEMV
-
- 19 Sep, 2023 3 commits
-
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper Hansen authored
-
- 15 Sep, 2023 7 commits
-
-
Casper authored
Safetensors and model sharding
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper authored
Allow user to use custom calibration data for quantization
-
Casper authored
-
Casper authored
-
Casper authored
-
- 14 Sep, 2023 4 commits
- 13 Sep, 2023 13 commits
-
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper authored
-
Casper authored
[NEW] GEMV kernel implementation
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper Hansen authored
-
Casper Hansen authored
-