Implementation of FlashAttention-2 for Nvidia Tesla V100 / Titan V
☆175Jun 30, 2026Updated 3 weeks ago
Alternatives and similar repositories for flash-attention-v100
Users that are interested in flash-attention-v100 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- forked from vllm-project/flash-attention☆58May 9, 2026Updated 2 months ago
- vLLM fork for Tesla V100 (SM70) with AWQ 4-bit support, CUDA 12.8 build flow, and validated Qwen3.5 27B/35B deployment on multi-GPU V…☆539Updated this week
- vLLM fork for Tesla V100 (SM70) — extends 1CatAI's AWQ support and adds GGUF support☆19Jun 20, 2026Updated last month
- This project is specifically developed for V100, based on lmdeploy 0.12.1, and supports mainstream open-source models from Q4 2025 to Q1 …☆21Mar 18, 2026Updated 4 months ago
- 1CatV2 with TileLANG written FA-v100 and many goodies☆17Jul 15, 2026Updated last week
- 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.
- marlin_v100 是一个从 vLLM 主树中提取出来的最小 Marlin 独立开发工作区，聚焦于 Marlin dense 与 Marlin MoE 的源码开发、最小构建和轻量验证。它保留了核心 CUDA/C++ 实现、最小 Python 薄封装、生成器测试与主树回写…☆19Jul 2, 2026Updated 2 weeks ago
- ☆78Feb 19, 2024Updated 2 years ago
- vllm混合推理扩展插件，支持多NUMA混合推理，单卡推理Qwen3-Next模型可达1000+ prefill☆34Nov 7, 2025Updated 8 months ago
- IMMA-based **FP8-as-storage** GEMM experiments for Ampere (sm_86 / RTX 3090 Ti).☆24Jan 30, 2026Updated 5 months ago
- Flash Attention 2 implementation for Turing GPUs☆116Mar 23, 2026Updated 3 months ago
- NVIDIA Linux open GPU with P2P support☆351Jul 13, 2026Updated last week
- ide-cap-chan is a utility for batch image captioning with natural language using various VL models☆14May 8, 2026Updated 2 months ago
- Lsglang is a special extension of sglang that fully utilizes CPU and GPU computing resources with an efficient GPU parallel + NUMA parall…☆97Updated this week
- Fast and memory-efficient exact attention☆22Jun 26, 2026Updated 3 weeks ago
- 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.
- A ComfyUI custom node implementation of TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows.☆44Mar 6, 2026Updated 4 months ago
- ML software (llama.cpp, ComfyUI, vLLM) builds for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆286Jul 8, 2026Updated last week
- Enable true multi gpu capability in Comfy UI using XDiT XFuser and FSDP managed by Ray☆368Updated this week
- Cross-platform FlashAttention-2 Triton implementation for Turing+ GPUs with custom configuration mode☆26Jan 12, 2026Updated 6 months ago
- Top ML papers of the week.☆46Updated this week
- High-performance GPU kernels for LLM inference in OpenAI Triton. Fused RMSNorm, SwiGLU, INT8 GEMM with benchmarks and roofline analysis.☆31Updated this week
- ☆20May 9, 2026Updated 2 months ago
- llama.cpp fork with TQ3_1S/4S CUDA kernels — 3.5-bit WHT quantization achieving Q4s quality at 10% smaller size. Based on RaBitQ-inspired…☆221Jul 6, 2026Updated 2 weeks ago
- The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with 100+ tok/s single-request decode…☆431Jul 13, 2026Updated last week
- 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.
- A plugin code to have a simple face instead of the Xiaozhi AI firmware☆26Mar 29, 2026Updated 3 months ago
- ☆142Jun 13, 2026Updated last month
- ComfyUI-Bagel is now available in ComfyUI, BAGEL is an open‑source multimodal foundation model with 7B active parameters (14B total) trai…☆29May 28, 2025Updated last year
- Processing of astronomical images☆14Updated this week
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"☆14Nov 22, 2024Updated last year
- Run DeepSeek-V4-Flash on SM89 (Ada / RTX 4090) with vLLM — patch over PR #41834. Validated on 4x RTX 4090.☆22Updated this week
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆125Updated this week
- 4-bit Shampoo for Memory-Efficient Network Training (NeurIPS 2024)☆13Feb 13, 2025Updated last year
- 一个基于利萨茹曲线的ComfyUI自定义节点,用于模拟平滑的手持相机抖动。A ComfyUI custom node for smooth handheld camera shake simulation based on Lissajous curves.☆47Feb 28, 2026Updated 4 months ago
- 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.
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆794Updated this week
- Sage attention for turning.☆70Dec 29, 2025Updated 6 months ago
- ik_llama.cpp's Thireus fork with release builds for macOS/Windows/Ubuntu CPU, Vulkan and CUDA☆165Updated this week
- R labs for the book OpenIntro Statistics (https://www.openintro.org/stat/)☆13Nov 17, 2016Updated 9 years ago
- Unified KV cache compression for LLM inference — TurboQuant, IsoQuant, PlanarQuant, TriAttention. 10 methods, GPU-validated, multi-GPU pl…☆24Jul 11, 2026Updated last week
- GPT2# is a zero dependency, sub 1 000 loc implementation of GPT2 inference, batteries included☆13May 2, 2023Updated 3 years ago
- ☆69Nov 11, 2025Updated 8 months ago