Qcompiler / MIXQLinks
MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction
☆94Updated last year
Alternatives and similar repositories for MIXQ
Users that are interested in MIXQ are comparing it to the libraries listed below
Sorting:
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆240Updated last year
- Support mixed-precsion inference with vllm☆84Updated 6 months ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆283Updated 9 months ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆276Updated last year
- Mixed precision inference by Tensorrt-LLM☆81Updated last year
- [ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2☆280Updated 5 months ago
- ☆102Updated 5 years ago
- SQuant [ICLR22]☆131Updated 3 years ago
- Official implementation of "MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Training"☆43Updated last year
- ☆204Updated 4 months ago
- official implementation of paper SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training☆44Updated last year
- Build CUDA Neural Network From Scratch☆22Updated last year
- Official code of "StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs".☆74Updated 7 months ago
- Official Implementation of "Accel-GNN: High-Performance GPU Accelerator Design for Graph Neural Networks"☆52Updated 10 months ago
- A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.☆187Updated 6 months ago
- The framework to prune LLMs to any size and any config.☆94Updated last year
- KFunca: A minimalist, high-performance GPU-based automatic differentiation framework☆29Updated 5 months ago
- Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+…☆160Updated 2 months ago
- [ECCV 2024] Efficient Inference of Vision Instruction-Following Models with Elastic Cache☆43Updated last year
- A deployment, monitoring and autoscaling service towards serverless LLM serving.☆151Updated 2 weeks ago
- [ICCV 2025] SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs☆81Updated 3 weeks ago
- A scalable, end-to-end training pipeline for general-purpose agents☆366Updated 7 months ago
- This is the official code repository of MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tas…☆85Updated 10 months ago
- FlagPerf is an open-source software platform for benchmarking AI chips.☆360Updated 2 months ago
- This is a repo for my NanoGPT Pytorch2.0 Implementation when torch2.0 released soon, faster and simpler, a good tutorial learning GPT.☆50Updated last year
- RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response☆42Updated last year
- 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☆161Updated 3 months ago
- This tool(enhance_long) aims to enhance the LlaMa2 long context extrapolation capability in the lowest-cost approach, preferably without …☆45Updated 2 years ago
- ☆95Updated 4 years ago
- Deep Learning Deployment Framework: Supports tf/torch/trt/trtllm/vllm and other NN frameworks. Support dynamic batching, and streaming mo…☆168Updated 9 months ago