Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).
☆143Jul 11, 2026Updated 4 months ago
Alternatives and similar repositories for GSQ
Users that are interested in GSQ are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- RCO: Optimization of Non-Decomposable Objectives under Exact Budget Constraints for LLM Quantization and Pruning☆78Jun 13, 2026Updated 5 months ago
- Statistically-Lossless Quantization of Large Language Models☆64Oct 8, 2026Updated last month
- Disaggregated quantization official codebase☆41Oct 21, 2026Updated 3 weeks ago
- ☆130Mar 18, 2026Updated 8 months ago
- ☆11Nov 16, 2024Updated 2 years 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.
- Official Repository for "WUSH: Near-Optimal Adaptive Transforms for LLM Quantization" (ICML 2026)☆18Jun 30, 2026Updated 4 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆102Sep 4, 2024Updated 2 years ago
- PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度☆1,707Updated this week
- ☆17Jul 9, 2026Updated 4 months ago
- Self-contained Python lib with zero-dependencies that give you a unified device properties for gpu, cpu, and npu. No more calling separat…☆18Oct 18, 2026Updated last month
- Secure P2P File Transfer Tool☆15Oct 10, 2026Updated last month
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…☆32Feb 17, 2025Updated last year
- Mixed-vendor GPU inference cluster manager with speculative decoding☆39Jul 2, 2026Updated 4 months ago
- Interactive AI storytelling app for Windows & Android with browser multiplayer, and local or API models.☆16Oct 15, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- DeepSeek-V4-Flash-0731 tuned on 4x DGX Spark (GB10) at TP=4 — 123.13 tok/s decode. Every variable measured one at a time, with the values…☆13Aug 11, 2026Updated 3 months ago
- ☆18Jun 16, 2026Updated 5 months ago
- ☆21Apr 27, 2026Updated 6 months ago
- llama.cpp patch: faster MoE offload for models that don't fit in VRAM☆88Updated this week
- ☆200Jun 22, 2025Updated last year
- Models and codes for INTERSPEECH 2023 paper DistilXLSR: A Light Weight Cross-Lingual Speech Representation Model☆13Mar 30, 2025Updated last year
- a libp2p-backed daemon wrapping the functionalities of go-libp2p for use in other languages☆12Feb 9, 2025Updated last year
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆25Oct 13, 2026Updated last month
- PlayTrain: LLM-generated JavaScript game environments for RL☆12Oct 8, 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.
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆12Oct 28, 2026Updated 3 weeks ago
- ☆13Aug 24, 2026Updated 2 months ago
- Official code for the paper "Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark"☆31Jun 30, 2025Updated last year
- Qwen3.8-27B EXL3 (4.00 bpw) + DFlash2 speculative decoding for ExLlamaV3, validated at 262k context on a 24 GB RTX 3090☆25Sep 20, 2026Updated last month
- ☆27Nov 5, 2026Updated last week
- Local-first book translation and LaTeX/PDF pipeline. Hy-MT2, MinerU, validated fragment cache and resumable builds. EN→RU and prepared DE…☆16Updated this week
- Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”☆212Apr 21, 2026Updated 6 months ago
- study of cutlass☆22Nov 10, 2024Updated 2 years ago
- [COLM 2025] DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined Rotation; 知乎:https://zhuanlan.zhihu.c…☆30Mar 5, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- SGLang-native serving for the Moet sign-symmetric W2 expert format with SM120 W2/W4 kernels, GLM-5.2 NVFP4 TP4 on 4x RTX PRO 6000☆20Jul 10, 2026Updated 4 months ago
- ☆190Sep 28, 2026Updated last month
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,840Updated this week
- NVFP4 Flash-Attention 4 on BlackWell☆69Sep 26, 2026Updated last month
- Build complete SillyTavern World Info / LoreBooks with an LLM — from a single idea or a guided, tabbed worldbuilding form. Video demo htt…☆19Aug 7, 2026Updated 3 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆338Updated this week
- Official repository of paper [FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic, NeurIPS 2025]☆22Dec 2, 2025Updated 11 months ago
Are these results useful?