A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 00:45 UTC
[Doc] Remove performance warning for auto_awq.md (#12743)
Michael Goin committed
Feb 5, 2025 at 01:43 UTC
c53dc466b1b802d45d0b61cce36908334ea7a23e
1 file changed
-6
docs/source/features/quantization/auto_awq.md
-6
@@ -2,12 +2,6 @@
2
3
# AutoAWQ
4
5
-:::{warning}
6
-Please note that AWQ support in vLLM is under-optimized at the moment. We would recommend using the unquantized version of the model for better
7
-accuracy and higher throughput. Currently, you can use AWQ as a way to reduce memory footprint. As of now, it is more suitable for low latency
8
-inference with small number of concurrent requests. vLLM's AWQ implementation have lower throughput than unquantized version.
9
-:::
10
-
5
To create a new 4-bit quantized model, you can leverage [AutoAWQ](https://github.com/casper-hansen/AutoAWQ).
6
Quantizing reduces the model's precision from FP16 to INT4 which effectively reduces the file size by ~70%.
7
The main benefits are lower latency and memory usage.