huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-24 08:22:07 +00:00
Code Issues Packages Projects Releases Wiki Activity
ce28ee88d5
text-generation-inference/integration-tests/models/__snapshots__/test_flash_llama_marlin
History
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
..
test_flash_llama_marlin_all_params.json Add support for Marlin-quantized models 2024-06-06 13:16:52 +02:00
test_flash_llama_marlin_load.json Add support for Marlin-quantized models 2024-06-06 13:16:52 +02:00
test_flash_llama_marlin.json Add support for Marlin-quantized models 2024-06-06 13:16:52 +02:00