Single-card Intel Gaudi2 vLLM source snapshot: FP8 Qwen, non-greedy DFlash2/MTP, GDN kernels and host-side optimizations.
☆17Nov 6, 2026Updated this week
Alternatives and similar repositories for gaudi2-single-card-vllm
Users that are interested in gaudi2-single-card-vllm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 使用nvidia oam转接卡将intel gaudi2转接到pcie并在ubuntu下正常驱动和使用的指南☆29Updated this week
- 1Cat-vLLM on Intel Gaudi☆46Oct 12, 2026Updated 3 weeks ago
- Container driven LLM control for VLLM & llama models☆14Oct 20, 2026Updated 2 weeks ago
- 把 Codex 原版 computer-use 运行时做成一个普通命令行工具。☆16Oct 28, 2026Updated last week
- 1Cat Studio: unified vLLM workbench, Codex Agent and creative canvas☆15Updated this 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.
- AMD R9700 Tuned Stack for vLLM and ROCM10☆39Updated this week
- ☆11Oct 18, 2026Updated 2 weeks ago
- Run AMD AITER's hand-written ASM kernels on CDNA2 / gfx90a (MI210, MI250). 242 of 1,422 kernels translated, with the tests and benchmarks…☆11Sep 9, 2026Updated last month
- A Pytorch Extention for CMP 170HX☆17Jun 29, 2026Updated 4 months ago
- 这回一定会熟练掌握日语五十音☆12Mar 29, 2023Updated 3 years ago
- Obleth is a high performance, fairshare AI gateway designed to be placed between the load balancer and an upstream provider like openai, …☆25Updated this week
- 限制问题区域显存 62906MiB / 65024MiB 支持驱动 610.57.04 ，修改显卡显示名称为NVIDIA Tesla A100☆13Aug 30, 2026Updated 2 months ago
- DeepSeek-V4.1-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 297 tok/s for one user, up to 868 tok/s at eight, 262K context, one-command c…☆22Updated this week
- 轻量化跨平台多服务器一站式监控平台，支持全平台使用☆12Oct 10, 2022Updated 4 years 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.
- AI Fitness Coach for Claude Code — Garmin / Coros / WHOOP / Apple Watch, Obsidian memory, bilingual (EN/CN) | 支持佳明·高驰·WHOOP·Apple Watch 的…☆33Oct 26, 2026Updated last week
- “Debian 小手机壳”，一个用来包装 手机的 Debian 安装介质的盒子设 计。☆12Oct 20, 2023Updated 3 years ago
- 批量文件内容检索工具，目前支持检索的文件类型：解析表格类型：xlsx、csv、xls、xlsm、xlam、xlsb。解析文本类型：txt、json、sql。☆10Jul 22, 2023Updated 3 years ago
- GUI Opencore configuration for hackintosh☆11Oct 7, 2026Updated 3 weeks ago
- Shape-specialized ROCm inference for Qwen3.8 Flash Next on RDNA4☆69Sep 25, 2026Updated last month
- ☆26Oct 20, 2026Updated 2 weeks 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 11 months ago
- DeepSeek-V4.1-Flash (764B) on 4×CMP 170HX: PP4 + shadow KV + EXL3 2bpw + DSpark + 512k ctx + native vision — patches, recipes, acceptance…☆15Sep 29, 2026Updated last month
- Tensor-Core selector unlock for RTX 4070 Ti Super☆29Oct 20, 2026Updated 2 weeks ago
- 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.
- Reproducible vLLM deployment for Qwen3.8-27B on dual RTX 2080 Ti 22GB with NVLink☆22Sep 7, 2026Updated last month
- glm-5.2 on too many 64 / 80 GB A100's☆22Sep 9, 2026Updated last month
- Understand your diffs before you merge them☆12Updated this week
- Async PLE SSD offload for Qwen3.8 Flash Next on a 64 GiB SM80 GPU: vLLM patch, setup guide, and measured PP/TG results.☆23Sep 24, 2026Updated last month
- ComfyUI MiniMax H3 inference optimizations for NVIDIA Tesla V100 (SM70)☆31Sep 29, 2026Updated last month
- 一个Turing专用vLLM分支，通过整合FlashInfer 0.6.18（PR #3526）与SM75后端门槛补丁（PR #47949），持续同步vLLM主线最新版本☆38Oct 11, 2026Updated 3 weeks ago
- vLLM for NVIDIA CMP 170HX (Ampere sm_80): fast, repeatable model serving on one card or several☆27Updated this week
- A fully native port of Super Smash Bros. (N64) for the Sega Dreamcast.☆16Oct 10, 2026Updated 3 weeks ago
- Modern Developer Portfolio Website☆11Aug 15, 2026Updated 2 months ago
- 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.
- HX 家族多功能工具箱：NVIDIA CMP 全系矿卡（30HX/40HX/50HX/70HX/90HX/170HX）工作台——固件解锁、型号伪装、双卡调度、动态省电、快照回滚。单文件免安装，前端与工具包全部内嵌。☆40Oct 25, 2026Updated last week
- vLLM fork for Tesla V100 (SM70) — extends 1CatAI's AWQ support and adds GGUF support☆26Jun 20, 2026Updated 4 months ago
- Antigravity 破甲工 程：二进制提示词补丁 / 规则技能 / 生命周期钩子 / IDE 等长补丁 / 模型后端改道☆38Oct 28, 2026Updated last week
- Stable, high-throughput inference server for multi-GPU NVIDIA V100 (SM70): Qwen3.8 Flash-Next with AWQ / NVFP4, multimodal input, CPU/dis…☆45Updated this week
- ☆29Jun 2, 2025Updated last year
- 简单记录一些东西: 一些精品神药(精神药品) | GAHT | 药娘炼成记 | Linux 备忘录☆23Jun 15, 2026Updated 4 months ago
- Pong in Haskell / Clash, running as software using SDL and as hardware targeting FPGAs☆10Apr 20, 2024Updated 2 years ago