update readme for instructions for usage with infinity

Please merge this PR for documentation update.

Launched on A100-40G, 32GB usage, batch-size=16

```
INFO 2024-11-12 22:13:40,975 infinity_emb INFO: infinity_server.py:89
Creating 1engines:
engines=['Alibaba-NLP/gte-Qwen2-7B-instruct']
INFO 2024-11-12 22:13:40,979 infinity_emb INFO: Anonymized telemetry.py:30
telemetry can be disabled via environment variable
`DO_NOT_TRACK=1`.
INFO 2024-11-12 22:13:40,987 infinity_emb INFO: select_model.py:64
model=`Alibaba-NLP/gte-Qwen2-7B-instruct` selected,
using engine=`torch` and device=`cuda`
INFO 2024-11-12 22:13:41,188 SentenceTransformer.py:216
sentence_transformers.SentenceTransformer
INFO: Load pretrained SentenceTransformer:
Alibaba-NLP/gte-Qwen2-7B-instruct

INFO 2024-11-12 22:41:25,069 SentenceTransformer.py:355
sentence_transformers.SentenceTransformer
INFO: 1 prompts are loaded, with the keys:
['query']
INFO 2024-11-12 22:41:26,143 infinity_emb INFO: Getting select_model.py:97
timings for batch_size=16 and avg tokens per
sentence=2
2.64 ms tokenization
32.47 ms inference
0.25 ms post-processing
35.36 ms total
embeddings/sec: 452.54
INFO 2024-11-12 22:41:27,721 infinity_emb INFO: Getting select_model.py:103
timings for batch_size=16 and avg tokens per
sentence=513
7.76 ms tokenization
765.84 ms inference
0.53 ms post-processing
774.13 ms total
embeddings/sec: 20.67
```

README.md

@@ -5622,6 +5622,18 @@ scores = (embeddings[:2] @ embeddings[2:].T) * 100
 print(scores.tolist())
 ```
 
+## Infinity_emb
+
+Usage via [infinity](https://github.com/michaelfeil/infinity), a MIT Licensed inference server.
+
+```
+# requires ~16-32GB VRAM NVIDIA Compute Capability >= 8.0
+docker run \
+-v $PWD/data:/app/.cache --gpus "0" -p "7997":"7997" \
+michaelf34/infinity:0.0.68-trt-onnx \
+v2 --model-id Alibaba-NLP/gte-Qwen2-7B-instruct --revision "refs/pr/38" --dtype bfloat16 --batch-size 8 --device cuda --engine torch --port 7997 --no-bettertransformer
+```
+
 ## Evaluation
 
 ### MTEB & C-MTEB