bytedance / ABQ-LLM
An acceleration library that supports arbitrary bit-width combinatorial quantization operations
☆223Updated 7 months ago
Alternatives and similar repositories for ABQ-LLM:
Users that are interested in ABQ-LLM are comparing it to the libraries listed below
- MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction☆88Updated 6 months ago
- [ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2☆201Updated last month
- Unified KV Cache Compression Methods for Auto-Regressive Models☆1,039Updated 4 months ago
- Support mixed-precsion inference with vllm☆83Updated 3 months ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆171Updated last week
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆248Updated 8 months ago
- Mixed precision inference by Tensorrt-LLM☆79Updated 6 months ago
- A highly optimized LLM inference acceleration engine for Llama and its variants.☆884Updated this week
- ☆106Updated 4 years ago
- [ICLR 2025] BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments☆36Updated 2 months ago
- Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+…☆131Updated last week
- SQuant [ICLR22]☆131Updated 2 years ago
- adds Sequence Parallelism into LLaMA-Factory☆471Updated last week
- The framework to prune LLMs to any size and any config.☆92Updated last year
- APOLLO: SGD-like Memory, AdamW-level Performance☆212Updated 2 weeks ago
- Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆124Updated last month
- TVM Documentation in Chinese Simplified / TVM 中文文档☆1,188Updated 3 weeks ago
- A toolkit enhances PyTorch with specialized functions for low-bit quantized neural networks.☆197Updated 10 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆121Updated last month
- [ECCV 2024] Efficient Inference of Vision Instruction-Following Models with Elastic Cache☆42Updated 9 months ago
- ☆35Updated 9 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆131Updated 3 months ago
- A sparse attention kernel supporting mix sparse patterns☆202Updated 2 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆100Updated 3 weeks 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☆152Updated 9 months ago
- JittorGeometric is a Jittor-based graph machine learning library.☆154Updated last week
- Official implementation of the ICLR 2024 paper AffineQuant☆25Updated last year
- MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler a…☆176Updated 3 weeks ago
- Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models☆174Updated 6 months ago
- A deployment, monitoring and autoscaling service towards serverless LLM serving.☆151Updated this week