hf_text-generation-inference/launcher
Daniël de Kok 4594e6faba 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
2024-06-06 13:16:52 +02:00
..
src Add support for Marlin-quantized models 2024-06-06 13:16:52 +02:00
Cargo.toml Upgrading to rust 1.78. (#1851) 2024-05-06 13:48:11 +02:00
build.rs chore(github): add templates (#264) 2023-05-02 15:43:19 +02:00