4-bit AWQ INT4 + NVFP4 quantization toolkit for ByteDance Lance multimodal model (image + video)
☆14May 20, 2026Updated 5 months ago
Alternatives and similar repositories for lance-quant
Users that are interested in lance-quant are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- My attempt of making the GGUF convertion easier☆14Aug 3, 2026Updated 2 months ago
- UI for Ace-Step-1.5 this UI use Api-Server☆16Apr 28, 2026Updated 5 months ago
- Triton-optimized ComfyUI custom node for Z-Image Base/Turbo | W8A8 Hadamard Rotation (ConvRot-style) | LoRA & ControlNet compatible | ~1.…☆24Apr 5, 2026Updated 6 months ago
- Lifting ControlNet for Generalized Depth Conditioning☆27Dec 28, 2023Updated 2 years ago
- Mini-SGLang is a mini version of SGLang project ().☆13Sep 24, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆12Nov 21, 2025Updated 11 months ago
- Fast INT4 model inference custom node for ComfyUI leveraging Tensor Cores.☆39Jul 10, 2026Updated 3 months ago
- W4A16 MoE GEMM CUDA kernel. Tuned for H200, B200 & B300.☆13Updated this week
- A lightweight CuTe-based CUDA kernel for DuoAttention, optimized for large language model inference.☆12Dec 25, 2025Updated 10 months ago
- CUDA Graph runtime tensor debugging utilities for PyTorch☆18Jul 12, 2026Updated 3 months ago
- Megakernel for Gated DeltaNet, optimized by PTO-ISA☆23Updated this week
- ☆13Mar 28, 2025Updated last year
- wxMaster是电脑版微信客户端的自动化框架，你可以用任何编程语言通过HTTP协议调用wxMaster框架的API接口，实现微信自动收发消息。☆13Apr 23, 2025Updated last year
- CuteDSL Swizzle Visualize Tool☆14Feb 22, 2026Updated 8 months ago
- 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.
- ☆16Jul 19, 2026Updated 3 months ago
- Grad course on ML systems☆24Updated this week
- ☆10Sep 12, 2024Updated 2 years ago
- PipeWeave: Synergizing Analytical and Learning Models for Unified GPU Performance Prediction☆23Sep 2, 2026Updated last month
- A toy simulator for multi-chiplet GPU☆24Apr 16, 2026Updated 6 months ago
- 🎓Automatically Update LLM inference systems Papers Daily using Github Actions (Update Every 12th hours)☆12Updated this week
- [NeurIPS 2026] Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion☆19Sep 25, 2026Updated last month
- This script merges multiple sharded safetensors files into a single safetensors file.☆48Apr 18, 2025Updated last year
- ☆17Jun 4, 2026Updated 4 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.
- ☆18Jun 19, 2026Updated 4 months ago
- An external memory allocator example for PyTorch.☆16Aug 10, 2025Updated last year
- A comprehensive study of related works and research around Google's Genie 3 model - a new frontier for world models☆15Aug 18, 2025Updated last year
- Fused MoE kernel☆23Updated this week
- A high performance development and dispatch library for high-performance machine learning kernels.☆38Aug 15, 2026Updated 2 months ago
- 西安电子科技大学学位论文 Typst 模板（硕士学术 / 专业学位、本科毕业设计论文）。☆16Sep 17, 2026Updated last month
- 自用的油猴脚本☆13Sep 6, 2026Updated last month
- Surgical GPU kernel benchmark: 7 hard problems, frontier coding agents, roofline-graded against hardware peak.☆19Jun 12, 2026Updated 4 months ago
- SC'25 UltraAttn: Efficiently Parallelizing Attention through Hierarchical Context-Tiling☆16Aug 14, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- codewithgpu.com python client package☆20May 18, 2023Updated 3 years ago
- Code and reproducibility artifacts for reconstructing megakernel persistence with CUDA PDL☆26Aug 5, 2026Updated 2 months ago
- Sequence-level 1F1B schedule for LLMs.☆19Jun 4, 2024Updated 2 years ago
- Custom node to load models in INT8 for 1.5~2X Speed gains on 30 series cards.☆311Jun 26, 2026Updated 3 months ago
- ☆14Jul 22, 2026Updated 3 months ago
- Autonomous CUDA kernel optimization agent with structured task specs and per-config scoring☆17Jun 17, 2026Updated 4 months ago
- Website for CSE 234, Winter 2025☆16Mar 24, 2025Updated last year