Qcompiler / vllm-mixed-precision
Support mixed-precsion inference with vllm
☆102Updated this week
Alternatives and similar repositories for vllm-mixed-precision:
Users that are interested in vllm-mixed-precision are comparing it to the libraries listed below
- MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction☆74Updated 2 months ago
- Mixed precision inference by Tensorrt-LLM☆71Updated 2 months ago
- This tool(enhance_long) aims to enhance the LlaMa2 long context extrapolation capability in the lowest-cost approach, preferably without …☆44Updated last year
- A toolkit enhances PyTorch with specialized functions for low-bit quantized neural networks.☆71Updated 6 months ago
- RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response☆36Updated 3 weeks ago
- Build CUDA Neural Network From Scratch☆15Updated 4 months ago
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆241Updated 3 months ago
- [ECCV 2024] Efficient Inference of Vision Instruction-Following Models with Elastic Cache☆41Updated 5 months ago
- [EMNLP 2024] DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models☆48Updated 2 months ago
- This repo contains my customised style python based plots for NLP papers, and includes my reproduction for my favourite papers' plots☆36Updated 10 months ago
- SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models☆39Updated 3 weeks ago
- Empower Your Model with Longer and Better Context Comprehention☆40Updated last year
- official implementation of paper SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training☆14Updated last month
- LLM Benchmark for Code☆31Updated 5 months ago
- The framework to prune LLMs to any size and any config.☆83Updated 10 months ago
- MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler a…☆157Updated 2 months ago
- [COLING Demos 2025] an Easy-to-use Tool for Comprehensive Response Evaluation of LLMs☆38Updated last month
- A Comprehensive Benchmark for Code Information Retrieval.☆58Updated last month
- 【高性能OpenAI LLM服务】通过GPRS+TensorRT-LLM+Tokenizers.cpp实现纯C++版高性能OpenAI LLM服务，支持chat和function call模式，支持ai agent，支持分布式多 卡推理，支持多模态，支持gradio聊天界面。☆87Updated this week
- High performance rank executor for advertisement and recommendation system, implemented in C/C++ and support ensembled into Java/Scala ho…☆72Updated 10 months ago
- ☆42Updated 6 months ago
- SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation☆66Updated last month
- 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☆165Updated 6 months ago
- Official Implementation of "Accel-GNN: High-Performance GPU Accelerator Design for Graph Neural Networks"☆49Updated last year
- ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆143Updated 2 months ago
- A python package that takes tables from a web page and processes them to get high quality tables☆46Updated 2 years ago
- ☆42Updated 3 months ago
- Code of Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Ne…☆26Updated 9 months ago
- Single-thread, end-to-end C++ implementation of the Bitnet (1.58-bit weight) model☆11Updated 2 months ago
- This includes the original implementation of CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control.☆56Updated 3 months ago