# Supported features

This section provides details on vLLM features supported on Qualcomm Cloud AI, including model coverage, serving capabilities, and performance optimizations.

## Model coverage

- [vLLM supported models](https://docs.qualcomm.com/doc/80-99100-3/topic/supported-models.html)
- [Embedding networks](https://docs.qualcomm.com/doc/80-99100-3/topic/Embedding-Networks.html)

## Execution, memory, and context management

- [Compute context length (CCL)](https://docs.qualcomm.com/doc/80-99100-3/topic/CCL.html)
- [Prefix caching](https://docs.qualcomm.com/doc/80-99100-3/topic/Prefix-Caching.html)

## Decoding, sampling, and output control

- [Speculative decoding](https://docs.qualcomm.com/doc/80-99100-3/topic/Speculative-Decoding.html)
- [On-device sampling support with vLLM](https://docs.qualcomm.com/doc/80-99100-3/topic/On-Device-Sampling.html)
- [Guided decoding](https://docs.qualcomm.com/doc/80-99100-3/topic/Guided-Decoding.html)
- [vLLM supports tool call parsing](https://docs.qualcomm.com/doc/80-99100-3/topic/Tool-Call-Parsing.html)

## Model optimization and adaptation

- [Quantization](https://docs.qualcomm.com/doc/80-99100-3/topic/Quantized-model.html)
- [LoRAX support with vLLM](https://docs.qualcomm.com/doc/80-99100-3/topic/LoRAX.html)

## Serving architecture and deployment

- [Disaggregated serving support with vLLM](https://docs.qualcomm.com/doc/80-99100-3/topic/Disaggregated-Serving.html)
- [Multimodality support with vLLM](https://docs.qualcomm.com/doc/80-99100-3/topic/Multimodality.html)
- [vLLM deployment using Kserve](https://docs.qualcomm.com/doc/80-99100-3/topic/Kserve.html)

## Configuration, compatibility, and reference

- [vLLM arguments for QAIC](https://docs.qualcomm.com/doc/80-99100-3/topic/input-args-env-variables.html)
- [Cross‑feature support matrix](https://docs.qualcomm.com/doc/80-99100-3/topic/Cross-Feature-Matrix.html)

Last Published: Aug 25, 2026

[Previous Topic
Benchmarking](https://docs.qualcomm.com/bundle/publicresource/80-99100-3/topics/benchmarking.md) [Next Topic
Build vLLM (optional)](https://docs.qualcomm.com/bundle/publicresource/80-99100-3/topics/build.md)