Update README.md
Browse files
README.md
CHANGED
@@ -20,9 +20,10 @@ pipeline_tag: text-generation
|
|
20 |
[Phi4-mini](https://huggingface.co/microsoft/Phi-4-mini-instruct) quantized with [torchao](https://huggingface.co/docs/transformers/main/en/quantization/torchao) int4 weight only quantization, using [hqq](https://mobiusml.github.io/hqq_blog/) algorithm for improved accuracy, by PyTorch team. Use it directly or serve using [vLLM](https://docs.vllm.ai/en/latest/) for 67% VRAM reduction and 12-20% speedup on A100 GPUs.
|
21 |
|
22 |
# Inference with vLLM
|
23 |
-
Need to install vllm nightly to get some recent changes:
|
24 |
```
|
25 |
pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
|
|
|
26 |
```
|
27 |
|
28 |
## Code Example
|
|
|
20 |
[Phi4-mini](https://huggingface.co/microsoft/Phi-4-mini-instruct) quantized with [torchao](https://huggingface.co/docs/transformers/main/en/quantization/torchao) int4 weight only quantization, using [hqq](https://mobiusml.github.io/hqq_blog/) algorithm for improved accuracy, by PyTorch team. Use it directly or serve using [vLLM](https://docs.vllm.ai/en/latest/) for 67% VRAM reduction and 12-20% speedup on A100 GPUs.
|
21 |
|
22 |
# Inference with vLLM
|
23 |
+
Need to install vllm nightly and torchao nightly to get some recent changes:
|
24 |
```
|
25 |
pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
|
26 |
+
pip install git+https://github.com/pytorch/ao.git
|
27 |
```
|
28 |
|
29 |
## Code Example
|