huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-15 10:26:33 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
b13a82a4387a55df07bec4e2eb6f7a8ebd0b98a2
candle/candle-core
History
Laurent Mazare b13a82a438 Separate quantized phi-3 implementation. (#2157) 
* Separate quantized phi-3 implementation.

* Integrate the quantized phi3 model.=

* Small fixes, get the generation to work properly.

* Keep the old llama implementation around.

* Change the default.
2024-05-04 10:14:57 +02:00
..
benches
Metal Unary: Add benchmarks and process kernels in a tile based fashion (#2056)
2024-04-21 00:10:33 +02:00
examples
Move the tensor-tools binary in a separate crate. (#1969)
2024-03-30 15:49:37 +01:00
src
Separate quantized phi-3 implementation. (#2157)
2024-05-04 10:14:57 +02:00
tests
Add the cuda dequantize f16 kernels. (#2137)
2024-04-28 20:05:05 +02:00
Cargo.toml
feat(bf16): add cast support + tests for cast + bin ops (#1524)
2024-01-11 15:49:13 +01:00
LICENSE
Refactor the hierarchy.
2023-06-27 11:57:27 +02:00
README.md
Refactor the hierarchy.
2023-06-27 11:57:27 +02:00

README.md

candle

Minimalist ML framework for Rust