TensorCash fork of vLLM — carries the proof-of-inference sampler path and FlatBuffer proof package used by vLLM-backed mining workers.
takakuni
8a36ef59da
Route step-counter increments through increment_steps(rows_tensor, rows_host=) instead of a bare steps[rows] += 1 / increment_steps(rows) without rows_host. The bare form left the optional steps_host mirror stale-but-valid, so with POW_STEPS_HOST_FASTPATH=1 check_pow_solutions would miss proof-window boundaries and drop shares. rows/valid_rows is the row set already on the host. |
||
|---|---|---|
| .gemini | ||
| benchmarks | ||
| cmake | ||
| csrc | ||
| docker | ||
| docs | ||
| examples | ||
| requirements | ||
| scripts | ||
| tests | ||
| tools | ||
| vllm | ||
| .clang-format | ||
| .coveragerc | ||
| .dockerignore | ||
| .git-blame-ignore-revs | ||
| .gitignore | ||
| .markdownlint.yaml | ||
| .pre-commit-config.yaml | ||
| .readthedocs.yaml | ||
| .shellcheckrc | ||
| .yapfignore | ||
| AGENTS.md | ||
| CLAUDE.md | ||
| CMakeLists.txt | ||
| CODE_OF_CONDUCT.md | ||
| codecov.yml | ||
| CONTRIBUTING.md | ||
| DCO | ||
| LICENSE | ||
| MANIFEST.in | ||
| mkdocs.yaml | ||
| NOTICE | ||
| pyproject.toml | ||
| README.md | ||
| RELEASE.md | ||
| SECURITY.md | ||
| setup.py | ||
| use_existing_torch.py | ||
This is a TensorCash fork of
vllm-project/vllmThis repository is part of TensorCash, useful proof-of-work for verifiable AI. This checkout is the
feature/pow-on-v0.19TensorCash branch.
- What changed: vLLM v0.19 carries the TensorCash proof-of-inference sampler path, FlatBuffer proof package,
extra_argsPoW routing, CPU-only PoW sampler tests, and the newer vLLM v0.19 worker/runtime base.- How it is used: consumed as
services/miner-api/vllm-v019by the umbrellatensorcash/tensorcashrepository.- Contributing: see the umbrella
CONTRIBUTING.md.The original upstream README follows unchanged.
Easy, fast, and cheap LLM serving for everyone
| Documentation | Blog | Paper | Twitter/X | User Forum | Developer Slack |
🔥 We have built a vllm website to help you get started with vllm. Please visit vllm.ai to learn more. For events, please visit vllm.ai/events to join us.
About
vLLM is a fast and easy-to-use library for LLM inference and serving.
Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.
vLLM is fast with:
- State-of-the-art serving throughput
- Efficient management of attention key and value memory with PagedAttention
- Continuous batching of incoming requests
- Fast model execution with CUDA/HIP graph
- Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8
- Optimized CUDA kernels, including integration with FlashAttention and FlashInfer
- Speculative decoding
- Chunked prefill
vLLM is flexible and easy to use with:
- Seamless integration with popular Hugging Face models
- High-throughput serving with various decoding algorithms, including parallel sampling, beam search, and more
- Tensor, pipeline, data and expert parallelism support for distributed inference
- Streaming outputs
- OpenAI-compatible API server
- 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.
- Prefix caching support
- Multi-LoRA support
vLLM seamlessly supports most popular open-source models on HuggingFace, including:
- Transformer-like LLMs (e.g., Llama)
- Mixture-of-Expert LLMs (e.g., Mixtral, Deepseek-V2 and V3)
- Embedding Models (e.g., E5-Mistral)
- Multi-modal LLMs (e.g., LLaVA)
Find the full list of supported models here.
Getting Started
Install vLLM with pip or from source:
pip install vllm
Visit our documentation to learn more.
Contributing
We welcome and value any contributions and collaborations. Please check out Contributing to vLLM for how to get involved.
Citation
If you use vLLM for your research, please cite our paper:
@inproceedings{kwon2023efficient,
title={Efficient Memory Management for Large Language Model Serving with PagedAttention},
author={Woosuk Kwon and Zhuohan Li and Siyuan Zhuang and Ying Sheng and Lianmin Zheng and Cody Hao Yu and Joseph E. Gonzalez and Hao Zhang and Ion Stoica},
booktitle={Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles},
year={2023}
}
Contact Us
- For technical questions and feature requests, please use GitHub Issues
- For discussing with fellow users, please use the vLLM Forum
- For coordinating contributions and development, please use Slack
- For security disclosures, please use GitHub's Security Advisories feature
- For collaborations and partnerships, please contact us at collaboration@vllm.ai
Media Kit
- If you wish to use vLLM's logo, please refer to our media kit repo