Qcompiler / MIXQLinks
MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction
☆90Updated 7 months ago
Alternatives and similar repositories for MIXQ
Users that are interested in MIXQ are comparing it to the libraries listed below
Sorting:
- Support mixed-precsion inference with vllm☆84Updated 5 months ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆200Updated last month
- Mixed precision inference by Tensorrt-LLM☆80Updated 8 months ago
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆224Updated 8 months ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆256Updated 9 months ago
- [ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2☆219Updated 3 months ago
- ☆106Updated 4 years ago
- official implementation of paper SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training☆38Updated 6 months ago
- A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.☆185Updated 2 weeks ago
- SQuant [ICLR22]☆131Updated 2 years ago
- Official Implementation of "Accel-GNN: High-Performance GPU Accelerator Design for Graph Neural Networks"☆49Updated 3 months ago
- Official implementation of "MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Training"☆38Updated last year
- Build CUDA Neural Network From Scratch☆21Updated 9 months ago
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆137Updated last month
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆78Updated 5 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆47Updated last week
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆53Updated last week
- Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+…☆140Updated last month
- ☆96Updated 9 months ago
- ☆77Updated 2 months ago
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆115Updated last year
- Implement Flash Attention using Cute.☆87Updated 6 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆126Updated 2 months ago
- ☆54Updated last year
- ☆141Updated 3 months ago
- Repo for SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting (ISCA25)☆37Updated last month
- Code Repository of Evaluating Quantized Large Language Models☆124Updated 9 months ago
- 16-fold memory access reduction with nearly no loss☆99Updated 2 months ago
- FlagPerf is an open-source software platform for benchmarking AI chips.☆338Updated this week
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆48Updated 11 months ago