Qcompiler / vllm-mixed-precisionLinks
Support mixed-precsion inference with vllm
☆84Updated 5 months ago
Alternatives and similar repositories for vllm-mixed-precision
Users that are interested in vllm-mixed-precision are comparing it to the libraries listed below
Sorting:
- Mixed precision inference by Tensorrt-LLM☆80Updated 8 months ago
- MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction☆90Updated 7 months ago
- This tool(enhance_long) aims to enhance the LlaMa2 long context extrapolation capability in the lowest-cost approach, preferably without …☆45Updated last year
- official implementation of paper SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training☆38Updated 6 months ago
- Official code of "StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs".☆42Updated last week
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆224Updated 8 months ago
- A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.☆185Updated 2 weeks ago
- RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response☆41Updated 6 months ago
- The framework to prune LLMs to any size and any config.☆93Updated last year
- SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models☆40Updated 4 months ago
- [ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2☆219Updated 3 months ago
- ☆54Updated last week
- [ECCV 2024] Efficient Inference of Vision Instruction-Following Models with Elastic Cache☆43Updated 11 months ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆203Updated last month
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆256Updated 9 months ago
- Official Implementation of "Pay Attention to What You Need"☆42Updated 4 months ago
- LLM Benchmark for Code☆30Updated 10 months ago
- ☆51Updated last week
- MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler a…☆178Updated 2 months ago
- This repo contains my customised style python based plots for NLP papers, and includes my reproduction for my favourite papers' plots☆39Updated last year
- Collecting personality-indicative data for role-playing agents.☆22Updated 4 months ago
- Hybrid Latent Reasoning via Reinforcement Learning☆120Updated 3 weeks ago
- Official Implementation of "Accel-GNN: High-Performance GPU Accelerator Design for Graph Neural Networks"☆49Updated 3 months ago
- ☆106Updated 4 years ago
- A Contamination-free Multi-task Language Understanding Benchmark [Official, ACL 2025]☆117Updated last month
- Single-thread, end-to-end C++ implementation of the Bitnet (1.58-bit weight) model☆13Updated 7 months ago
- 使用deepspeed从头开始训练一个LLM,经过pretrain和sft阶段,验证llm学习知识、理解语言、回答问题的能力☆154Updated 11 months ago
- Build CUDA Neural Network From Scratch☆21Updated 9 months ago
- Code of Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Ne…☆26Updated last year
- [EMNLP 2024] DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models☆70Updated 2 weeks ago