diff options
author | Laurent Mazare <laurent.mazare@gmail.com> | 2024-04-01 00:15:48 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2024-04-01 00:15:48 +0200 |
commit | cd29c7ccd420a840d883361c290ee92d06b9b96c (patch) | |
tree | d387a1f1af623de2e50751d493d541eb3789684c /candle-core/src/tensor.rs | |
parent | f9954b73bac9fed91a9a08d952adc1cfb836a568 (diff) | |
download | candle-cd29c7ccd420a840d883361c290ee92d06b9b96c.tar.gz candle-cd29c7ccd420a840d883361c290ee92d06b9b96c.tar.bz2 candle-cd29c7ccd420a840d883361c290ee92d06b9b96c.zip |
More ggml cuda kernels (#1977)
* Add more cuda kernels for quantized matmul.
* Add the vec-dot bits.
* Expose the quantized matmul-vec kernels.
* Also include the quantize-q8-1 kernel.
* Glue code for the q8-1 quantization.
* mm-vec product via q8-1 quantization.
* Add a test.
* Add a mm test.
* Get the test to return some sensible results.
* Also test dmmv.
* Fix the launch params.
* Allow for tweaking the force_dmmv parameter while it's experimental.
Diffstat (limited to 'candle-core/src/tensor.rs')
0 files changed, 0 insertions, 0 deletions