huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-21 23:12:07 +00:00
Code Issues Packages Projects Releases Wiki Activity
63cd798a19
text-generation-inference/integration-tests
History
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
..
images Pali gemma modeling (#1895) 2024-07-17 05:36:58 +00:00
models Add support for Marlin-quantized models 2024-09-24 03:38:05 +00:00
conftest.py Add support for exl2 quantization 2024-09-24 03:19:39 +00:00
poetry.lock fix: improve tool type, bump pydantic and outlines (#1650) 2024-04-25 12:34:55 +03:00
pyproject.toml v2.0.1 2024-06-03 15:39:47 +03:00
pytest.ini chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
requirements.txt fix: improve tool type, bump pydantic and outlines (#1650) 2024-04-25 12:34:55 +03:00