bytedance / ABQ-LLMLinks
An acceleration library that supports arbitrary bit-width combinatorial quantization operations
☆232Updated 11 months ago
Alternatives and similar repositories for ABQ-LLM
Users that are interested in ABQ-LLM are comparing it to the libraries listed below
Sorting:
- MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction☆93Updated 10 months ago
- [ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2☆237Updated 5 months ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆263Updated last year
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆236Updated 4 months ago
- Unified KV Cache Compression Methods for Auto-Regressive Models☆1,229Updated 7 months ago
- A highly optimized LLM inference acceleration engine for Llama and its variants.☆900Updated last month
- Support mixed-precsion inference with vllm☆85Updated last month
- SQuant [ICLR22]☆130Updated 2 years ago
- ☆105Updated 4 years ago
- Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+…☆153Updated 3 months ago
- Mixed precision inference by Tensorrt-LLM☆81Updated 10 months ago
- FlagPerf is an open-source software platform for benchmarking AI chips.☆345Updated last month
- A scalable, end-to-end training pipeline for general-purpose agents☆355Updated last month
- The framework to prune LLMs to any size and any config.☆94Updated last year
- A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.☆185Updated last month
- [ICML 2025] "SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator"☆541Updated last month
- APOLLO: SGD-like Memory, AdamW-level Performance; MLSys'25 Oustanding Paper Honorable Mention☆253Updated 4 months ago
- TVM Documentation in Chinese Simplified / TVM 中文文档☆2,204Updated 4 months ago
- ☆847Updated this week
- Deep Learning Deployment Framework: Supports tf/torch/trt/trtllm/vllm and other NN frameworks. Support dynamic batching, and streaming mo…☆166Updated 3 months ago
- [ICLR 2025] BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments☆36Updated 6 months ago
- Official code of "StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs".☆68Updated 2 months ago
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆156Updated last month
- [ICCV 2025] SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs☆70Updated last month
- adds Sequence Parallelism into LLaMA-Factory☆551Updated last week
- A deployment, monitoring and autoscaling service towards serverless LLM serving.☆153Updated last week
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆138Updated last week
- Build CUDA Neural Network From Scratch☆21Updated 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☆156Updated last month
- [ECCV 2024] Efficient Inference of Vision Instruction-Following Models with Elastic Cache☆42Updated last year