FlashAttention brought back to Tesla V100 — a deep llama.cpp fork: SM 7.0 D256 kernels, SplitKV3, q4_0 KV cache, DFlash2 speculative decoding and multimodal fixes.
☆19Oct 23, 2026Updated this week
Alternatives and similar repositories for sm70-attn
Users that are interested in sm70-attn are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- xllama.cpp — Optimized LLM Inference for NVidia Tesla V100-SXM2-32GB☆17Apr 29, 2026Updated 6 months ago
- Next generation PowerPC library for classic AmigaOS (work in progress)☆13Feb 5, 2024Updated 2 years ago
- Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.☆23Jul 10, 2026Updated 3 months ago
- This is a fork of prismml-eng/llama.cpp + amesianx/turboquant with support for TurboQuant and prism-ml/ternary-bonsai-27b-gguf (2-bit).☆17Jul 16, 2026Updated 3 months ago
- View instruction register through GameGuardian !☆14Dec 8, 2019Updated 6 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- 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
- A command line tool for playing with Linux 5.13's Landlock feature☆13Apr 16, 2021Updated 5 years ago
- Some crackme i built for Android☆11Apr 15, 2020Updated 6 years ago
- https://gist.github.com/akihikodaki/87df4149e7ca87f18dc56807ec5a1bc5 VirGL virtual OpenGL renderer☆19Oct 15, 2026Updated 2 weeks ago
- ComfyUI custom node: run MiniMax H3 at near-fp16 speed with near-fp32 numerical stability on GPUs without bf16/fp8 hardware (V100 sm_70)☆19Aug 22, 2026Updated 2 months ago
- ☆12Sep 21, 2022Updated 4 years 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…☆33Oct 7, 2026Updated 3 weeks ago
- UPnP MediaRenderer for the commandline☆15Feb 11, 2013Updated 13 years ago
- Experimental Windows kernel driver PoCs for detecting manually mapped drivers via big pool enumeration, PTE walking, CFG data-pointer hoo…☆21Apr 26, 2026Updated 6 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Compiled binary including working synlinks☆12Feb 1, 2015Updated 11 years ago
- Terraform | Infrastructure as Code!☆16Sep 26, 2022Updated 4 years ago
- ☆18Jun 16, 2024Updated 2 years ago
- Amiga OpenPCI library under LGPL license☆16May 17, 2016Updated 10 years ago
- Technical analysis library written in TypeScript.☆14Apr 29, 2019Updated 7 years ago
- Sameple of Hide memory from maps☆14Jan 28, 2023Updated 3 years ago
- Collaborative Commons for Blockchain and Cryptocurrency Curation☆10Jun 5, 2023Updated 3 years ago
- A maubot plugin to set expiration times on messages in a room☆10Sep 29, 2026Updated 3 weeks ago
- docker images with VBCC compiler for AmigaOS 3, 4 and Morphs cross compiling☆23Sep 11, 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.
- 可运行的Claude代码源码,采用双端模型进行驱动☆17Apr 5, 2026Updated 6 months ago
- The APK Decompile GUI tools for MacOS☆10Feb 23, 2024Updated 2 years ago
- Indicators used in cryptotrading-hub☆10May 2, 2025Updated last year
- vLLM fork for pascal gpu☆18Mar 13, 2026Updated 7 months ago
- Docker build scripts for TornadoVM on GPUs: https://github.com/beehive-lab/TornadoVM☆32Oct 9, 2026Updated 2 weeks ago
- llama.cpp optimized for NVIDIA Tesla V100 (SM70): Qwen3.8-Flash-Next with MTP (prefill 3402 tok/s at 200K context on 6x V100-16GB; also r…☆61Updated this week
- OWASP Foundation Web Respository☆23Jun 2, 2026Updated 4 months ago
- A feature-incomplete peekahole (pahole) clone that doesn't rely on libdwarves (and doesn't choke on Clang output)☆24Oct 23, 2017Updated 9 years ago
- SKRoot Pro 奥创版 - Linux 6.6内核ROOT工具☆18Feb 1, 2026Updated 8 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.
- Sol-Attn (arXiv 2607.24027) sparse acceleration for MiniMax H3 on V100 — single-node ComfyUI plugin (embedded FP16Safe + keep-or-drop ker…☆34Aug 29, 2026Updated 2 months ago
- The set-and-forget LLM engine for Pascal and Volta: PXQ codec + kernels, auto-tuned per card. Ready-to-run PXQ models in MODELS.md; bench…☆90Updated this week
- Unlocks full compute, PCIe Gen2 and ReBar support for CMP 50HX mining cards. Same performance as RTX 2080 Ti achieved. One click install.☆99Oct 10, 2026Updated 2 weeks ago
- 解锁自有 NVIDIA CMP 170HX / 90HX 的算力限制。Linux x86-64，需要 root。☆58Aug 6, 2026Updated 2 months ago
- The GRUB2 signing extension are some scripts which help you to verify, sign and unsign your GRUB2 bootloader files using GPG.☆23Jul 22, 2021Updated 5 years ago
- Single-binary Raspberry Pi monitor that collects system metrics, stores them in local SQLite, and serves live dashboards and threshold al…☆19Oct 22, 2026Updated last week
- Just the new Clash of Clans crypto core☆28Sep 25, 2018Updated 8 years ago