Skip to content

Commit 0b37108

Browse files
authored
docs: overhaul user documentation (#1730)
Signed-off-by: AlpinDale <alpindale@gmail.com>
1 parent 5bd5d3d commit 0b37108

71 files changed

Lines changed: 7312 additions & 6673 deletions

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

README.md

Lines changed: 84 additions & 73 deletions
Original file line numberDiff line numberDiff line change
@@ -1,88 +1,99 @@
1-
<h1 align="center">
2-
Breathing Life into Language
3-
</h1>
1+
<h1 align="center">Sonar</h1>
42

5-
![sonar](assets/sonar.jpg)
3+
![Sonar](assets/sonar.jpg)
64

7-
Sonar (formerly Aphrodite Engine) is an inference engine that optimizes the serving of HuggingFace-compatible models at scale. Built on vLLM's Paged Attention technology, it delivers high-performance model inference for multiple concurrent users. Sonar serves as the backend engine powering the [Dolphin Inference Network](https://datagen.dphn.ai) and [PygmalionAI](https://pygmalion.chat)'s chat platforms and API infrastructure.
5+
Sonar is an inference engine for Hugging Face-compatible language and
6+
multimodal models. It provides continuous batching, paged KV-cache management,
7+
optimized kernels, quantization, speculative decoding, and distributed
8+
serving.
89

9-
Sonar builds upon and integrates the exceptional work from [various projects](#acknowledgements), primarily [vLLM](https://vllm.ai).
10+
Sonar is based on [vLLM](https://github.com/vllm-project/vllm). It includes
11+
additional model and quantization formats, sampling methods, kernels, platforms,
12+
and deployment features.
13+
It serves production workloads for the
14+
[Dolphin Inference Network](https://datagen.dphn.ai) and
15+
[PygmalionAI](https://pygmalion.chat).
1016

11-
## Features
17+
## Documentation
1218

13-
- Continuous Batching
14-
- Efficient K/V management with [PagedAttention](https://vllm.ai) from vLLM
15-
- Optimized CUDA kernels for improved inference
16-
- Quantization support via [AQLM](https://arxiv.org/abs/2401.06118), [AutoRound](https://arxiv.org/abs/2309.05516), [AWQ](https://arxiv.org/abs/2306.00978), [BitNet](https://arxiv.org/abs/2310.11453), [Bitsandbytes](https://arxiv.org/abs/2208.07339), [ExLlamaV3](https://github.com/turboderp-org/exllamav3), [GGUF](https://github.com/ggml-org/llama.cpp), [GPTQ](https://arxiv.org/abs/2210.17323), [QuIP#](https://arxiv.org/abs/2402.04396), [SqueezeLLM](https://arxiv.org/abs/2306.07629), [Marlin](https://arxiv.org/abs/2408.11743), [[2]](https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/examples/fp8_primer.html) [[3]](https://developer.nvidia.com/blog/introducing-nvfp4-for-efficient-and-accurate-low-precision-inference/), [NVIDIA ModelOpt](https://github.com/NVIDIA/TensorRT-Model-Optimizer), [TorchAO](https://github.com/pytorch/ao), [VPTQ](https://arxiv.org/abs/2409.17066), [compressed_tensors](https://github.com/vllm-project/llm-compressor), [MXFP4](https://huggingface.co/blog/RakshitAralimatti/learn-ai-with-me), and more.
17-
- Distributed inference
18-
- Quantized KV cache using scaled and scale-less FP8, and TurboQuant
19-
- Support for modern samplers such as DRY, XTC, Mirostat, and more
20-
- Disaggregated inference
21-
- Speculative decoding, including EAGLE, DFlash, ngram, MTP, and more
22-
- Multimodal support
23-
- Multi-LoRA support
19+
Read the documentation at [sonar.dphn.ai](https://sonar.dphn.ai/).
2420

25-
## Quickstart
21+
- [Installation](https://sonar.dphn.ai/getting-started/installation/)
22+
- [Supported models](https://sonar.dphn.ai/reference/models/)
23+
- [Quantization support](https://sonar.dphn.ai/reference/quantization/)
24+
- [Server arguments](https://sonar.dphn.ai/reference/server-arguments/)
25+
- [Optimization](https://sonar.dphn.ai/deployment/optimization/)
26+
- [Parallelism](https://sonar.dphn.ai/deployment/parallelism/)
27+
- [Production deployment](https://sonar.dphn.ai/deployment/production/)
2628

27-
Install the engine (the Python package and CLI keep the historical `aphrodite` name for now):
29+
The model, quantization, and server-argument references are generated from the
30+
current source tree.
2831

29-
```sh
30-
pip install -U aphrodite-engine
31-
```
32-
33-
Then launch a model:
34-
35-
```sh
36-
aphrodite run Qwen/Qwen3.5-0.8B
37-
```
38-
39-
This will create a [OpenAI](https://platform.openai.com/docs/api-reference/)-compatible API server that can be accessed at port 2242 of the localhost. You can plug in the API into a UI that supports OpenAI, such as [SillyTavern](https://github.com/SillyTavern/SillyTavern).
40-
41-
## Requirements
42-
43-
- Operating System: Linux, Windows (WSL2)
44-
- Python: 3.10 to 3.13 (build from source for 3.14)
45-
46-
#### Build Requirements
32+
## Install
4733

48-
- CUDA >= 12
34+
The published NVIDIA wheel supports Linux x86-64, Python 3.10-3.13, and NVIDIA
35+
GPUs with compute capability 8.0 or newer.
4936

50-
### Notes
37+
Install [uv](https://docs.astral.sh/uv/getting-started/installation/), then
38+
create an environment:
5139

52-
1. By design, Sonar takes up 92% of your GPU's VRAM. If you're not serving an LLM at scale, you may want to limit the amount of memory it takes up. You can do this in the API example by launching the server with the `--gpu-memory-utilization 0.6` (0.6 means 60%).
53-
54-
2. You can view the full list of commands by running `aphrodite run --help`.
55-
56-
## Acknowledgements
57-
58-
Sonar would have not been possible without the phenomenal work of other open-source projects. A (non-exhaustive) list:
59-
60-
- [vLLM](https://github.com/vllm-project/vllm)
61-
- [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM)
62-
- [xFormers](https://github.com/facebookresearch/xformers)
63-
- [Flash Attention](https://github.com/Dao-AILab/flash-attention)
64-
- [llama.cpp](https://github.com/ggerganov/llama.cpp)
65-
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ)
66-
- [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ)
67-
- [SqueezeLLM](https://github.com/SqueezeAILab/SqueezeLLM/)
68-
- [Exllamav2](https://github.com/turboderp/exllamav2)
69-
- [TabbyAPI](https://github.com/theroyallab/tabbyAPI)
70-
- [AQLM](https://github.com/Vahe1994/AQLM)
71-
- [KoboldAI](https://github.com/henk717/KoboldAI)
72-
- [Text Generation WebUI](https://github.com/oobabooga/text-generation-webui)
73-
- [Megatron-LM](https://github.com/NVIDIA/Megatron-LM)
74-
- [Ray](https://github.com/ray-project/ray)
75-
76-
### Sponsors
40+
```bash
41+
uv venv --python 3.12 --seed
42+
source .venv/bin/activate
43+
uv pip install aphrodite-engine --torch-backend=cu130
44+
```
7745

78-
Past and present, in alphabetical order:
46+
Use the [complete installation guide](https://sonar.dphn.ai/getting-started/installation/)
47+
for AMD ROCm, Intel XPU, CPU, Apple silicon, Google TPU, Docker, WSL 2, source
48+
builds, and nightly wheels.
7949

80-
- [Arc Compute](https://www.arccompute.io/)
81-
- [Lium](https://lium.io)
82-
- [Prime Intellect](https://www.primeintellect.ai/)
83-
- [PygmalionAI](https://pygmalion.chat)
84-
- [Ruliad AI](https://ruliad.ai)
50+
## Serve a model
8551

86-
## Contributing
52+
```bash
53+
aphrodite serve Qwen/Qwen3-0.6B \
54+
--served-model-name qwen3
55+
```
8756

88-
Everyone is welcome to contribute. You can support the project by opening Pull Requests for new features, fixes, or general UX improvements.
57+
The server listens on `http://127.0.0.1:2242` by default. It provides
58+
OpenAI-compatible APIs, health checks, metrics, and an OpenAPI schema.
59+
60+
See the [OpenAI-compatible API guide](https://sonar.dphn.ai/serving/openai/)
61+
for streaming, embeddings, tool calls, reasoning output, and Sonar request
62+
parameters.
63+
64+
## Key features
65+
66+
- Continuous batching and paged KV-cache management
67+
- Prefix caching enabled by default
68+
- Tensor, pipeline, data, and expert parallelism
69+
- Multi-node multiprocessing without a Ray cluster
70+
- Prefill/decode disaggregation through NIXL and other KV connectors
71+
- Quantized weights and FP8 KV cache
72+
- Speculative decoding with MTP, EAGLE, DSpark, DFlash, n-gram, and other
73+
methods
74+
- Structured output, reasoning parsers, and automatic tool calling
75+
- Image, audio, and video model support
76+
- LoRA adapter serving
77+
- Prometheus metrics and health endpoints
78+
- OpenAI, Anthropic, pooling, scoring, reranking, transcription, and Kobold
79+
APIs
80+
81+
Support depends on the model, device, data type, and quantization method. Check
82+
the generated [model matrix](https://sonar.dphn.ai/reference/models/) and
83+
[quantization matrix](https://sonar.dphn.ai/reference/quantization/) before
84+
deployment.
85+
86+
Read the [optimization guide](https://sonar.dphn.ai/deployment/optimization/)
87+
before you tune scheduler, cache, compilation, quantization, or speculative
88+
decoding settings.
89+
90+
## Development
91+
92+
```bash
93+
git clone https://github.com/dphnAI/sonar.git
94+
cd sonar
95+
uv venv --python 3.13 --seed --prompt sonar
96+
source .venv/bin/activate
97+
APHRODITE_USE_PRECOMPILED=1 \
98+
uv pip install --editable . --torch-backend=cu130
99+
```

docs/CNAME

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
aphrodite.pygmalion.chat
1+
sonar.dphn.ai

docs/astro.config.mjs

Lines changed: 49 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -22,41 +22,70 @@ export default defineConfig({
2222
},
2323
},
2424
],
25-
title: 'Aphrodite Engine',
25+
title: 'Sonar',
2626
social: {
27-
github: 'https://github.com/aphrodite-engine/aphrodite-engine',
27+
github: 'https://github.com/dphnAI/sonar',
2828
},
2929
sidebar: [
3030
{
31-
label: 'Installation',
32-
autogenerate: { directory: 'installation' },
33-
31+
label: 'Start',
32+
items: [
33+
{ label: 'Choose a path', slug: 'getting-started/choose-a-path' },
34+
{ label: 'Install Sonar', slug: 'getting-started/installation' },
35+
{ label: 'Quickstart', slug: 'getting-started/quickstart' },
36+
{ label: 'Upgrade Sonar', slug: 'getting-started/upgrading' },
37+
],
3438
},
3539
{
36-
label: 'Usage',
37-
autogenerate: { directory: 'usage' },
40+
label: 'Use Sonar',
41+
items: [
42+
{ label: 'Python LLM API', slug: 'guides/offline-inference' },
43+
{ label: 'Sampling and structured output', slug: 'guides/sampling-and-structured-output' },
44+
{ label: 'OpenAI-compatible API', slug: 'serving/openai' },
45+
{ label: 'Other APIs', slug: 'serving/other-apis' },
46+
],
3847
},
3948
{
40-
41-
label: 'Adapters',
42-
autogenerate: { directory: 'adapters' },
49+
label: 'Deploy',
50+
items: [
51+
{ label: 'Optimize a deployment', slug: 'deployment/optimization' },
52+
{ label: 'Benchmarking', slug: 'deployment/benchmarking' },
53+
{ label: 'Choose parallelism', slug: 'deployment/parallelism' },
54+
{ label: 'Distributed deployment', slug: 'deployment/distributed' },
55+
{ label: 'Production deployment', slug: 'deployment/production' },
56+
{ label: 'Deployment recipes', slug: 'deployment/recipes' },
57+
{ label: 'Model loading and storage', slug: 'deployment/model-storage' },
58+
{ label: 'Security', slug: 'deployment/security' },
59+
{ label: 'Observability', slug: 'features/observability' },
60+
],
4361
},
4462
{
45-
label: 'Developer',
46-
autogenerate: { directory: 'developer' },
63+
label: 'Features',
64+
items: [
65+
{ label: 'Feature guide', slug: 'features' },
66+
{ label: 'LoRA adapters', slug: 'features/lora' },
67+
{ label: 'Prefix caching', slug: 'features/prefix-caching' },
68+
{ label: 'Speculative decoding', slug: 'features/speculative-decoding' },
69+
{ label: 'Tool calling', slug: 'features/tool-calling' },
70+
{ label: 'Reasoning and tool parsers', slug: 'features/reasoning-and-tools' },
71+
{ label: 'Multimodal inputs', slug: 'features/multimodal' },
72+
{ label: 'Observability', slug: 'features/observability' },
73+
],
4774
},
4875
{
49-
label: 'Prompt Caching',
50-
autogenerate: { directory: 'prompt-caching' },
76+
label: 'Help',
77+
items: [
78+
{ label: 'Troubleshooting', slug: 'troubleshooting' },
79+
],
5180
},
5281
{
53-
label: 'Quantization',
54-
autogenerate: { directory: 'quantization' },
82+
label: 'Reference',
83+
items: [
84+
{ label: 'Supported models', slug: 'reference/models' },
85+
{ label: 'Quantization support', slug: 'reference/quantization' },
86+
{ label: 'Server arguments', slug: 'reference/server-arguments' },
87+
],
5588
},
56-
{
57-
label: 'Spec Decoding',
58-
autogenerate: { directory: 'spec-decoding' },
59-
},
6089
],
6190
}),
6291
],

docs/src/content/docs/adapters/lora.md

Lines changed: 0 additions & 94 deletions
This file was deleted.

0 commit comments

Comments
 (0)