# INFERENCE

- [Why is inference important?](https://training.continuumlabs.ai/inference/why-is-inference-important.md): Speed and cost counts
- [Grouped Query Attention](https://training.continuumlabs.ai/inference/why-is-inference-important/grouped-query-attention.md)
- [Key Value Cache](https://training.continuumlabs.ai/inference/why-is-inference-important/key-value-cache.md): Managing model memory usage
- [Flash Attention](https://training.continuumlabs.ai/inference/why-is-inference-important/flash-attention.md)
- [Flash Attention 2](https://training.continuumlabs.ai/inference/why-is-inference-important/flash-attention-2.md): The seminal July 2023 paper
- [StreamingLLM](https://training.continuumlabs.ai/inference/why-is-inference-important/streamingllm.md)
- [Paged Attention and vLLM](https://training.continuumlabs.ai/inference/why-is-inference-important/paged-attention-and-vllm.md)
- [TensorRT-LLM](https://training.continuumlabs.ai/inference/why-is-inference-important/tensorrt-llm.md)
- [Torchscript](https://training.continuumlabs.ai/inference/why-is-inference-important/torchscript.md)
- [NVIDIA L40S GPU](https://training.continuumlabs.ai/inference/why-is-inference-important/nvidia-l40s-gpu.md): Low cost inference
- [Triton Inference Server - Introduction](https://training.continuumlabs.ai/inference/why-is-inference-important/triton-inference-server-introduction.md)
- [Triton Inference Server](https://training.continuumlabs.ai/inference/why-is-inference-important/triton-inference-server.md)
- [FiDO: Fusion-in-Decoder optimised for stronger performance and faster inference](https://training.continuumlabs.ai/inference/why-is-inference-important/fido-fusion-in-decoder-optimised-for-stronger-performance-and-faster-inference.md): Google Research, December 2022
- [Is PUE a useful measure of data centre performance?](https://training.continuumlabs.ai/inference/why-is-inference-important/is-pue-a-useful-measure-of-data-centre-performance.md)
- [SLORA](https://training.continuumlabs.ai/inference/why-is-inference-important/slora.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://training.continuumlabs.ai/inference.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.