Commit Graph

2 Commits

Author SHA1 Message Date
Daniël de Kok
136fb7e9b9 Add pytest release marker (#2114)
* Add pytest release marker

Annotate a test with `@pytest.mark.release` and it only gets run
with `pytest integration-tests --release`.

* Mark many models as `release` to speed up CI
2024-09-24 03:52:50 +00:00
Daniël de Kok
77ac0f364b Add support for Marlin-quantized models
This change adds support for Marlin-quantized models. Marlin is an
FP16xINT4 matmul kernel, which provides good speedups decoding batches
of 16-32 tokens. It supports quantized models with symmetric
quantization, groupsize -1 or 128, and 4-bit.

Tested with:

- Llama 2
- Llama 3
- Phi 3
2024-09-24 03:38:05 +00:00