Block-FP8 (W8A16) on NVIDIA V100 / Volta (sm_70) for vLLM — the FP8 path upstream drops on Volta, tuned for sparse MoE.
☆14Jul 10, 2026Updated 3 months ago
Alternatives and similar repositories for vllm-fp8-w8a16-sm70
Users that are interested in vllm-fp8-w8a16-sm70 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.☆23Jul 10, 2026Updated 3 months ago
- 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…☆26Jul 2, 2026Updated 3 months ago
- vLLM fork for Tesla V100☆15May 31, 2026Updated 5 months ago
- Qwen3.8-27B in native NVFP4/FP8 on 2x PCIe Tesla V100-32GB (SM70): the PCIe runbook for v100-skinny + 1Cat-vLLM, with the 3 fixes that ma…☆15Sep 13, 2026Updated last month
- FlashAttention brought back to Tesla V100 — a deep llama.cpp fork: SM 7.0 D256 kernels, SplitKV3, q4_0 KV cache, DFlash2 speculative deco…☆19Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A Simple Tool to gather information from any website, domain, sub-domain, DNS, links by enumeration with simple commands.☆18Jun 7, 2024Updated 2 years ago
- Auto-built Docker image of 1Cat-vLLM for NVIDIA Tesla V100 (sm_70/Volta) with CUDA 12.8 — rebuilt daily when upstream releases☆12Jul 22, 2026Updated 3 months ago
- Worm is an Android post exploitation Framework to gain remote access of any Android device by exploiting Android Debug Bridge.☆19Jun 7, 2024Updated 2 years ago
- a simple keylogger that records hardware inputs like keyboard, mouse, microphone and webcam and sends it to your e-mail.☆22Oct 18, 2024Updated 2 years 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
- 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…☆64Oct 23, 2026Updated last week
- Hand-written NVFP4 W4A16 CUDA kernels for Volta☆178Aug 19, 2026Updated 2 months ago
- CUDA implementation of Filecoin's PC2 operation☆12Jun 20, 2023Updated 3 years ago
- SGLang for cool dudes using V100☆82Oct 5, 2026Updated 3 weeks 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.
- 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
- HideMePlease is a new generation tool to hide phising web links into legitimate web links with original domains (eg: facebook.com, instag…☆33Jun 3, 2024Updated 2 years ago
- HorizonPush is a file-sharing and synchronization tool leveraging iroh for peer-to-peer transfers and multi-provider blob streaming. It p…☆16Apr 3, 2025Updated last year
- 一个为 Qwen-Code 提供响应式 Web 界面的项目，让您可以从任何设备进行 AI 辅助编程。☆17Sep 8, 2026Updated last month
- Voice typing for Windows. local & cloud ASR (Seed-ASR 2.0 )豆包语音输入法,FireRedASR2,Qwen audio/ASR,microsoft/mai-transcribe-2,MIMO ASR☆18Oct 19, 2026Updated last week
- 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…☆34Oct 7, 2026Updated 3 weeks ago
- llama-cpp support turboquant and gemma 4☆20May 19, 2026Updated 5 months ago
- SemiFA: Agentic Multi-Modal Framework for Autonomous Semiconductor Failure Analysis Report Generation | LangGraph · LLaVA-1.6 · DINOv2 · …☆16Apr 16, 2026Updated 6 months ago
- VENDORIZED in lucebox-hub. Fork of llama.cpp, ggml graph for lucebox inference engine☆30Jul 8, 2026Updated 3 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.
- Rust SurrealDB Tutoria☆20Oct 15, 2023Updated 3 years ago
- vLLM fork for Tesla V100 (SM70) — extends 1CatAI's AWQ support and adds GGUF support☆26Jun 20, 2026Updated 4 months ago
- Leveraging Optical Character Recognition (OCR) technology to automatically read container numbers directly from images, offering innovati…☆17Jan 6, 2024Updated 2 years ago
- Last updated~ 26/03/2026 Old layouts can be viewed here - https://github.com/COUNTRY-HUMANS/old-readme & https://github.com/COUNTRY-HUMA…☆38Oct 10, 2026Updated 3 weeks ago
- This is the official **live** mirror of Ascend-native hardware plugin for ray☆16Jul 3, 2026Updated 3 months ago
- A Vue directive that prevents vertical scrolling outside the current element when top or bottom are reached.☆20Feb 8, 2018Updated 8 years ago
- ☆17Mar 17, 2025Updated last year
- ☆15Updated this week
- V100 / SM70-focused vLLM engineering fork for modern LLM inference.☆1,431Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- This crate provides core types for interoperating with IPLD.☆34Feb 17, 2026Updated 8 months ago
- 毕业设计:基于SpringBoot及thymeleaf搭建的疫情信息管理系统☆12Sep 27, 2020Updated 6 years ago
- Refined types for Typescript☆26Aug 18, 2017Updated 9 years ago
- SpringBoot示例项目☆20Mar 31, 2022Updated 4 years ago
- ☆14Mar 11, 2014Updated 12 years ago
- 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
- ☆35Oct 20, 2025Updated last year