Flash Attention v2 for Pascal (P100, GTX 1080) and Volta (V100) GPUs — bringing O(N) memory attention to hardware the official flash-attn doesn't support.
☆27Apr 4, 2026Updated 6 months ago
Alternatives and similar repositories for flash-attention-legacy
Users that are interested in flash-attention-legacy are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Show the time in Roman Numerals☆12Jan 23, 2020Updated 6 years ago
- Hindsight Memory for Open WebUI☆17May 27, 2026Updated 4 months ago
- BROKEN REPO. DO NOT USE UNDER ANY CIRCUMSTANCES☆20Oct 13, 2026Updated last week
- Run MiniMax H3 at native fp16 on pre-bf16 GPUs (V100/Volta) — exact-math fix for the black-frame overflows, ~11× faster than the fp32 fal…☆55Aug 8, 2026Updated 2 months ago
- Fast & lightweight interface for running Nano Banana LLM and compact local models on your PC. Optimized for high-speed AI interactions.☆44Mar 17, 2026Updated 7 months ago
- 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.
- Galahad by Corbenic☆49Oct 4, 2026Updated 2 weeks ago
- A 4B decision model: calibrated probabilities for yes/no, choice and score questions over long inputs.☆42Updated this week
- Unlocking NVIDIA CMP 90HX (GA102): kernel 6.12☆38Aug 22, 2026Updated 2 months ago
- Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.☆23Jul 10, 2026Updated 3 months ago
- Demonstrate a method to run a Python script from an IBMi RPGLE program. This example uses Python (launched by RPG) to create basic file d…☆10Dec 8, 2022Updated 3 years ago
- Implementation of FlashAttention-2 for Nvidia Tesla V100 / Titan V☆214Oct 14, 2026Updated last week
- An attempt to use Nvidia CMP cards for Machine Learning.☆33Jun 14, 2026Updated 4 months ago
- Unlocks full compute, PCIe Gen2 and ReBar support for CMP 50HX mining cards. Same performance as RTX 2080 Ti achieved. One click install.☆89Oct 10, 2026Updated last week
- Flexible OrcaSlicer for the Snapmaker U1 - Color Patch prints painted surfaces as a shell over a different-material core (soft grip on a …☆41Updated 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.
- Builds vLLM for ROCm gfx906 using Nix☆17Aug 29, 2026Updated last month
- VGGT implemented in C++☆14Mar 31, 2026Updated 6 months ago
- Proxima lets existing GPUs serve 4x more concurrent requests☆26Aug 19, 2026Updated 2 months ago
- HikVision IP Camera Alarm Server to MQTT☆14Sep 20, 2023Updated 3 years ago
- Type hints for DaVinci Resolve scripting Python library☆16Jul 11, 2026Updated 3 months ago
- Tiny vi-like text editor in only 100 lines of C++ code!☆14Aug 12, 2022Updated 4 years ago
- A ComfyUI custom node enabling **Flash Attention 1** on legacy NVIDIA GPUs (Tesla V100, T4) that lack Compute Capability 8.0+ required by…☆31Feb 9, 2026Updated 8 months ago
- Agentic-coding oriented inference engine for N x V100-SXM2, based on SGLang: GLM-5.3-Flash, Qwen3.8-Flash-Next, DeepSeek-V4.1-Flash, Mini…☆32Oct 7, 2026Updated 2 weeks ago
- Sol-Attn (arXiv 2607.24027) sparse acceleration for MiniMax H3 on V100 — single-node ComfyUI plugin (embedded FP16Safe + keep-or-drop ker…☆33Aug 29, 2026Updated last month
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆12Jul 10, 2025Updated last year
- This repository contains code used for our Multi Sentence Inference NAACL'22 paper.☆12Mar 6, 2023Updated 3 years ago
- FlashAttention-style custom attention backend for vLLM on AMD MI50/MI60/Radeon VII (gfx906). Downstream fork of mixa3607/ML-gfx906 with r…☆16Apr 22, 2026Updated 6 months ago
- ComfyUI node for Qwen-Image-2.1: 17 photographic styles (camera language + mood) via a PE-T2I prompt rewriter. Not a model loader.☆17Sep 23, 2026Updated 3 weeks ago
- ☆19Jun 1, 2025Updated last year
- Benchmarks, compose files, and findings for running Qwen3.6 (27B dense + 35B-A3B MoE) on 4× RTX 3090. vLLM/AWQ vs llama.cpp/GGUF, MTP spe…☆21Aug 15, 2026Updated 2 months ago
- Evaluate Transformers from the Hub 🔥☆14Sep 24, 2026Updated 3 weeks ago
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆242Sep 14, 2026Updated last month
- A proxy that hosts multiple single-model runners such as LLama.cpp and vLLM☆12May 30, 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.
- Extract text information from warc files☆12Sep 1, 2022Updated 4 years ago
- ☆12Feb 19, 2025Updated last year
- gfx906 setup document☆14Sep 1, 2025Updated last year
- SGLang for cool dudes using V100☆80Oct 5, 2026Updated 2 weeks ago
- All-In-One Network Security Dashboard☆28Sep 14, 2026Updated last month
- Latest firmware for antsdr E310 based on PlutoSDR☆18Aug 7, 2022Updated 4 years ago
- ☆14Dec 3, 2023Updated 2 years ago