REAP: Router-weighted Expert Activation Pruning for SMoE compression
☆536Apr 17, 2026Updated 6 months ago
Alternatives and similar repositories for reap
Users that are interested in reap are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- REAM: Merging Improves Pruning of Experts in LLMs☆28Apr 16, 2026Updated 6 months ago
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,763Updated this week
- PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率，量化感知训练的精度☆1,694Updated this week
- State-of-the-art LLM compression, built for production inference with vLLM☆3,927Updated this week
- llama.cpp fork with additional SOTA quants and improved performance☆3,352Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Official code for the paper "Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark"☆31Jun 30, 2025Updated last year
- ☆28Aug 15, 2026Updated 2 months ago
- ☆65Jul 10, 2025Updated last year
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆345Aug 19, 2026Updated 2 months ago
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆932Updated this week
- An Open Source Toolkit For LLM Distillation☆1,088May 12, 2026Updated 5 months ago
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,964Updated this week
- Produce your own Dynamic 3.0 Quants and achieve optimum accuracy & SOTA quantization performance! Input a target size and the toolchain w…☆171Sep 11, 2026Updated last month
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆5,465Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Tools for merging pretrained large language models.☆7,424Oct 22, 2026Updated last week
- Enhancing LLMs with LoRA☆230Updated this week
- ☆21Aug 6, 2026Updated 2 months ago
- A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official …☆560Updated this week
- Large-scale LLM inference engine☆1,898Updated this week
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆481Oct 14, 2026Updated 2 weeks ago
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,208Aug 18, 2026Updated 2 months ago
- easy exllama interface w/ automation & evals☆19Sep 25, 2026Updated last month
- MiniMax-H3 on single DGX Spark: keys Sol-Engine ports + Heretic TE + Spectrum/Sage speed + 0.5MP upscaler finish. Formal bench included.☆49Aug 23, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- slime is an LLM training framework for RL Scaling.☆8,762Updated this week
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆111Jun 20, 2025Updated last year
- JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Causal Parallel Tree Drafting☆241Updated this week
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,836Updated this week
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆204Sep 2, 2026Updated last month
- Mixture-of-Basis-Experts for Compressing MoE-based LLMs☆41Dec 24, 2025Updated 10 months ago
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆340Updated this week
- Open quantization tooling for TurboQuant-style low-bit LLM releases, stock GGUF deployment, and Apple Silicon runtime experiments.☆10May 5, 2026Updated 5 months ago
- Realtime TUI and web dashboard for multi-node NVIDIA DGX Spark clusters, with 200G ConnectX-7 RDMA fabric telemetry☆13Oct 24, 2026Updated last week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Transplants vocabulary between language models, enabling the creation of draft models for speculative decoding WITHOUT retraining.☆54Oct 29, 2025Updated last year
- A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular…☆589Sep 4, 2026Updated last month
- A fast inference library for running LLMs locally on modern consumer-class GPUs☆4,648Mar 4, 2026Updated 7 months ago
- Code for the paper *Attention Drift: What Speculative Decoding Models Learn*.☆33May 12, 2026Updated 5 months ago
- Archived: b12x development has moved to FlashInfer. See README for migration and PR-porting guidance.☆268Oct 6, 2026Updated 3 weeks ago
- Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”☆209Apr 21, 2026Updated 6 months ago
- ☆127Feb 26, 2026Updated 8 months ago