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 make it work without NVLink. 61-74 tok/s decode, MTP speculative decoding, OpenAI-compatible.
☆15Sep 13, 2026Updated last month
Alternatives and similar repositories for Nvidia-Tesla-v100-nvfp4-pcie
Users that are interested in Nvidia-Tesla-v100-nvfp4-pcie are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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
- Hand-written NVFP4 W4A16 CUDA kernels for Volta☆178Aug 19, 2026Updated 2 months ago
- Firefox-in-a-Docker for desktop use.☆10Aug 20, 2017Updated 9 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…☆34Oct 7, 2026Updated 3 weeks ago
- ⚠️ development has moved to VibePod☆14Feb 7, 2026Updated 8 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.
- DeepSeek Harness 开源手机端（iOS / Android PWA）：局域网扫码配对桌面 Host，无需账号，浏览任务并继续 Agent 对话。☆14Sep 10, 2026Updated last month
- GPT powered chat app optimized for studying☆11Nov 21, 2024Updated last year
- ☆16Oct 20, 2026Updated last week
- High-performance single-GPU inference for RTX 5090 Mobile.☆20Oct 4, 2026Updated 3 weeks ago
- NInfer on Tesla V100 (sm_70): Qwen3.8-27B deployment, build/convert scripts, systemd service, and cross-engine benchmark (vs llama.cpp). …☆52Sep 15, 2026Updated last month
- 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
- Implementation of BitNet-1.58 instruct tuning☆33Apr 14, 2024Updated 2 years ago
- 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
- Qwen3.8-27B on one DGX Spark GB10: DFlash 2 for 65 tok/s C1 and 120 C4; EAGLE 3/1/4 for ~191 C8, ~330 C16 and ~535 C32; native 262K, pinn…☆13Oct 6, 2026Updated 3 weeks 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.
- Wavefront Reconstruction Algorithms☆15Dec 19, 2017Updated 8 years ago
- Bonsai-27B x NInfer local deployment project (RTX 5080, ternary quantization)☆50Oct 6, 2026Updated 3 weeks 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
- 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
- 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
- An easy way to generate a table of contents for your markdown file☆24Feb 23, 2021Updated 5 years ago
- Claude AI session manager for tmux☆24Apr 16, 2026Updated 6 months ago
- 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
- vLLM fork for Tesla V100☆15May 31, 2026Updated 5 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.
- Truthful scheduler-step and streaming visualization for local LLM inference☆35Sep 6, 2026Updated last month
- Experimental implementation of DeepSeek v4 flaash in llama.cpp☆24Apr 30, 2026Updated 6 months ago
- ☆31Oct 19, 2025Updated last year
- gummy-translator 是一个实时翻译字幕工具，通过调用百炼平台的 Gummy 实时语音翻译模型和 SiliconFlow CosyVoice 流式语音合成，实现低延迟、实时的同声传译和实时双语字幕。☆30Apr 11, 2025Updated last year
- Dockerfile for Android Studio Development Environment☆34Jul 30, 2017Updated 9 years ago
- 用 git 命令点麦当劳：add 放购物车，rebase 凑最省，push 确认后才下单；card 生成 1024 吃麦贡献图（3D 汉堡天际线 / 年度小票）。基于麦当劳 MCP Server，附 --demo 无 Token 试玩和 Agent Skill。非官方参赛作…☆85Oct 13, 2026Updated 2 weeks ago
- Writing library for yee light blue using python for raspberry pi☆32May 6, 2017Updated 9 years ago
- Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.☆23Jul 10, 2026Updated 3 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
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- SpringBoot示例项目☆20Mar 31, 2022Updated 4 years ago
- Image galley saver plus☆21Jul 14, 2026Updated 3 months ago
- LLM inference in C/C++☆34Jan 27, 2026Updated 9 months 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
- Free AI short video generator that runs fully in the browser — no install, no GPU, no credit card. Type an idea, AI splits it into scenes…☆33Sep 28, 2026Updated last month
- Flash Attention v2 for Pascal (P100, GTX 1080) and Volta (V100) GPUs — bringing O(N) memory attention to hardware the official flash-attn…☆29Updated this week
- csdn下载，csdn免积分下载，csdn免会员下载，csdn付费内容下载☆20Apr 8, 2026Updated 6 months ago