A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 5, 09:45 UTC
[Docs] Bring README updates into docs README (#39397)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Apr 9, 2026 at 12:35 UTC
d87fb264df266652813a5c9347b1088a189e06c7
1 file changed
+27
-13
docs/README.md
+27
-13
@@ -25,7 +25,7 @@ hide:
25
26
vLLM is a fast and easy-to-use library for LLM inference and serving.
27
28
-Originally developed in the [Sky Computing Lab](https://sky.cs.berkeley.edu) at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.
28
+Originally developed in the [Sky Computing Lab](https://sky.cs.berkeley.edu) at UC Berkeley, vLLM has grown into one of the most active open-source AI projects built and maintained by a diverse community of many dozens of academic institutions and companies from over 2000 contributors.
29
30
Where to get started with vLLM depends on the type of user. If you are looking to:
31
@@ -42,23 +42,37 @@ vLLM is fast with:
42
43
- State-of-the-art serving throughput
44
- Efficient management of attention key and value memory with [**PagedAttention**](https://blog.vllm.ai/2023/06/20/vllm.html)
45
-- Continuous batching of incoming requests
46
-- Fast model execution with CUDA/HIP graph
47
-- Quantization: [GPTQ](https://arxiv.org/abs/2210.17323), [AWQ](https://arxiv.org/abs/2306.00978), INT4, INT8, and FP8
48
-- Optimized CUDA kernels, including integration with FlashAttention and FlashInfer.
49
-- Speculative decoding
50
-- Chunked prefill
45
+- Continuous batching of incoming requests, chunked prefill, prefix caching
46
+- Fast and flexible model execution with piecewise and full CUDA/HIP graphs
47
+- Quantization: FP8, MXFP8/MXFP4, NVFP4, INT8, INT4, GPTQ/AWQ, GGUF, compressed-tensors, ModelOpt, TorchAO, and [more](https://docs.vllm.ai/en/latest/features/quantization/index.html)
48
+- Optimized attention kernels including FlashAttention, FlashInfer, TRTLLM-GEN, FlashMLA, and Triton
49
+- Optimized GEMM/MoE kernels for various precisions using CUTLASS, TRTLLM-GEN, CuTeDSL
50
+- Speculative decoding including n-gram, suffix, EAGLE, DFlash
51
+- Automatic kernel generation and graph-level transformations using torch.compile
52
+- Disaggregated prefill, decode, and encode
53
54
vLLM is flexible and easy to use with:
55
54
-- Seamless integration with popular HuggingFace models
56
+- Seamless integration with popular Hugging Face models
57
- High-throughput serving with various decoding algorithms, including *parallel sampling*, *beam search*, and more
56
-- Tensor, pipeline, data and expert parallelism support for distributed inference
58
+- Tensor, pipeline, data, expert, and context parallelism for distributed inference
59
- Streaming outputs
58
-- OpenAI-compatible API server
59
-- Support for NVIDIA GPUs, AMD CPUs and GPUs, Intel CPUs and GPUs, PowerPC CPUs, Arm CPUs, and TPU. Additionally, support for diverse hardware plugins such as Intel Gaudi, IBM Spyre and Huawei Ascend.
60
-- Prefix caching support
61
-- Multi-LoRA support
60
+- Generation of structured outputs using xgrammar or guidance
61
+- Tool calling and reasoning parsers
62
+- OpenAI-compatible API server, plus Anthropic Messages API and gRPC support
63
+- Efficient multi-LoRA support for dense and MoE layers
64
+- Support for NVIDIA GPUs, AMD GPUs, and x86/ARM/PowerPC CPUs. Additionally, diverse hardware plugins such as Google TPUs, Intel Gaudi, IBM Spyre, Huawei Ascend, Rebellions NPU, Apple Silicon, MetaX GPU, and more.
65
+
66
+vLLM seamlessly supports 200+ model architectures on HuggingFace, including:
67
+
68
+- Decoder-only LLMs (e.g., Llama, Qwen, Gemma)
69
+- Mixture-of-Expert LLMs (e.g., Mixtral, DeepSeek-V3, Qwen-MoE, GPT-OSS)
70
+- Hybrid attention and state-space models (e.g., Mamba, Qwen3.5)
71
+- Multi-modal models (e.g., LLaVA, Qwen-VL, Pixtral)
72
+- Embedding and retrieval models (e.g., E5-Mistral, GTE, ColBERT)
73
+- Reward and classification models (e.g., Qwen-Math)
74
+
75
+Find the full list of supported models [here](./models/supported_models.md).
76
77
For more information, check out the following:
78