SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression
☆204May 15, 2026Updated 6 months ago
Alternatives and similar repositories for spectralquant
Users that are interested in spectralquant are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Kernels by MakoraGenerate☆15May 26, 2026Updated 5 months ago
- ☆12May 15, 2026Updated 6 months ago
- ☆17Jun 15, 2026Updated 5 months ago
- turboquant-based compression engine for LLM KV cache☆60Apr 3, 2026Updated 7 months ago
- Sequential Monte Carlo Speculative Decoding☆53Aug 25, 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.
- Open quantization tooling for TurboQuant-style low-bit LLM releases, stock GGUF deployment, and Apple Silicon runtime experiments.☆10May 5, 2026Updated 6 months ago
- KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44…☆1,059Apr 23, 2026Updated 6 months ago
- Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and …☆577Updated this week
- Triton kernels for dynamic causal short convolutions.☆35Jun 4, 2026Updated 5 months ago
- ☆16Jul 21, 2026Updated 3 months ago
- NanoGPT speedrun in JAX. Originally at https://nor-git.pages.dev/modded-nanogpt-jax/☆17Aug 28, 2025Updated last year
- TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained …☆870Aug 4, 2026Updated 3 months ago
- Self-improving long-term memory for AI coding agents (Claude Code & Cursor)☆13Mar 13, 2026Updated 8 months ago
- Lucebox inference engine for heterogeneous hardware & consumer GPUs☆3,007Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Statistically-Lossless Quantization of Large Language Models☆63Oct 8, 2026Updated last month
- world-model-mcp is a signed audit memory server for AI coding agents, delivered as an MCP tool. Every event Ed25519-signed and Merkle-cha…☆24Sep 15, 2026Updated 2 months ago
- Experimental llama.cpp fork for inference research and development☆909Updated this week
- CroissAttn: FP4 attention forward and backward, with analysis of stochastic rounding, zero-sum softmax gradients, and sampled centering.☆16Oct 25, 2026Updated 3 weeks ago
- Find the MLP neuron that makes a chat model become something, in minutes on one GPU.☆14Oct 28, 2026Updated 2 weeks ago
- Official repository for Parallax (Parameterized Local Linear Attention)☆71Jul 30, 2026Updated 3 months ago
- Triton kernels and PyTorch ops for Block Attention Residuals (AttnRes)☆90May 29, 2026Updated 5 months ago
- ☆17Jun 18, 2026Updated 4 months ago
- ☆307Apr 5, 2026Updated 7 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Run a coding model at 300+ tok/s on your Mac. Native Rust + Metal inference engine for LiquidAI LFM2.5-24B-A2B (MLX 4-bit) on Apple Silic…☆27Oct 29, 2026Updated 2 weeks ago
- ☆16Updated this week
- Algorithms for latent compaction☆278Apr 22, 2026Updated 6 months ago
- Deploy an AI chatbot in one click from your terminal☆10Aug 24, 2025Updated last year
- Open, calibrated, single-pass typed-decision models (4B & 27B) for finance and trading☆43Oct 1, 2026Updated last month
- [NeurIPS 2026] When Reasoning Meets Its Laws☆38Jan 2, 2026Updated 10 months ago
- Maps packages to source code. Allows coding agents to search any dependency with grep.☆34Mar 6, 2026Updated 8 months ago
- A zero-allocation, header-only C++ BPE tokenizer for Qwen, built for maximum inference throughput.☆24Apr 3, 2026Updated 7 months ago
- ☆14Sep 30, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Cross-GPU KV Cache Marketplace☆27Nov 12, 2025Updated last year
- ☆12Oct 9, 2025Updated last year
- ☆41Nov 1, 2026Updated 2 weeks ago
- mKernel: fast multi-node, multi-GPU fused kernels☆311Updated this week
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆344Aug 19, 2026Updated 2 months ago
- Parameter-efficient fine-tuning of LLMs using QLoRA — 4-bit quantization, PEFT adapters, W&B experiment tracking☆14Oct 13, 2026Updated last month
- Unofficial CLI and MCP server for Lambda cloud GPU instances☆21Jan 14, 2026Updated 10 months ago
Are these results useful?