jerryzh168 commited on
Commit
b20cbe9
·
verified ·
1 Parent(s): e3fc1c2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
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