A migration benchmark that measures whether production GPU Triton kernels — extracted from vLLM and SGLang inference paths — can be ported to the Huawei Ascend 910B (Atlas A2) via `triton-ascend` without losing correctness or performance.
☆136Oct 15, 2026Updated this week
Alternatives and similar repositories for TritonAscendBench
Users that are interested in TritonAscendBench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A privacy-conscious, local-first workbench for writing books in Markdown and plain text.☆95Aug 20, 2026Updated last month
- Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-…☆1,006Updated this week
- ☆674Oct 8, 2026Updated last week
- ☆820Updated this week
- Ten Engines. One local-first Harness OS.☆217Sep 22, 2026Updated 3 weeks ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- 一站式学习与求职平台，集刷题、OJ、课程、面试、AI 助手、社区、协同编辑于一体。☆74Oct 7, 2026Updated last week
- ☆256Updated this week
- Self-hosted two-way Notion and CalDAV sync on Cloudflare Workers + D1 or Node.js + PostgreSQL☆275Oct 8, 2026Updated last week
- MinerProxy矿池抽水 矿池代理 矿池中转 矿池抽水 纯中转Rust全新独立架构矿池中转 / 算力抽水工具 TCMinerProxy；近年全球大型矿场主流 Stratum 矿池代理，支持算力分流、自建私有矿池、TMS 加密隧道，适配全币种比特币挖矿等POW 算力运维…☆1,171Oct 9, 2026Updated last week
- A custom Agent OS built to be hackable, heavily inspired by OpenClaw.☆484Aug 7, 2026Updated 2 months ago
- A persistent LLM-maintained knowledge system for technical manuals, SOPs, and operational documentation.☆180Sep 16, 2026Updated last month
- ☆230Updated this week
- Run Linux-style commands on Windows via deterministic bash→PowerShell translation. No VM, no WSL. MCP server + CLI built for AI agents (C…☆994Updated this week
- FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware ro…☆3,342Sep 29, 2026Updated 2 weeks 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.
- ☆1,356Updated this week
- 基于 AI Agent 的产业园区项目管理研究 · 原型验证平台（Prototype，不代表最终产出产品）☆101Sep 17, 2026Updated last month
- 软件实习项目作业☆1,086Sep 2, 2026Updated last month
- MCPHub Desktop 是一款基于 Tauri 2 构建的桌面客户端，用于在个人电脑上统一管理 MCP服务器、Skills、RAG 知识库。所有进程、配置、密钥与向量数据都运行/保存在用户自己的机器上，不依赖任何远端服务。☆874Updated this week
- A beginner foundation skill for AI coding agents — from product idea, data and Git to security, deployment and launch.☆37Updated this week
- An open-source virtual AI Infra team that discovers, benchmarks, and safely upgrades local LLM inference—with independent quality gates, …☆97Sep 8, 2026Updated last month
- 般若波罗蜜。回到每一个争吵和沉默的节点，看看另一个版本的结局。☆875Sep 17, 2026Updated last month
- Context compression for MCP. Same upstream call, exact results recoverable.☆186Aug 14, 2026Updated 2 months ago
- Agent Skill 步进治理体系：由程序保证 Agent 不跳步骤（step-gate Rust 门控 + 交付门 + 链治理）☆479Sep 5, 2026Updated last month
- 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.
- This system can help bridge the gap between Codex and Claude Code, making it simple to refine a plan until it is complete, or to conduct …☆484Aug 11, 2026Updated 2 months ago
- Native vLLM serving for Jev decision models☆607Updated this week
- 把简历编辑交给前端，把内容润色交给 Agent☆198Updated this week
- 5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.☆1,222Sep 23, 2026Updated 3 weeks ago
- An AI agent command-line interface — multi-model LLM access, streaming terminal UI, tool calling, permission control, and session persist…☆120Updated this week
- Fast multi-modal decision model☆820Sep 29, 2026Updated 2 weeks ago
- dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressi…☆110Oct 10, 2026Updated last week
- Reusable multi-round research skill for evidence-backed product, market, technical, open-source, and investment-style surveys.☆105Sep 29, 2026Updated 2 weeks ago
- IdempotencyLab(幂等契约测试框架)：自动模拟并发、超时重试、MQ 重复消费等线上异常场景，验证支付 / 电商 / 库存系统的接口、MQ 消费与回调幂等实现是否真正可靠。☆100Aug 30, 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.
- Operant Beta：以多模型分工、按需通信、分层审批和经验复用为核心设计，在本机组织可追溯的 Agent 协作，并通过模块化架构扩展能力。☆416Updated this week
- LLM agent 的有界自纠错长期记忆层：把连续、含矛盾的项目交互日志蒸馏成有界、可自更新的记忆库。Bounded, self-correcting long-term memory for LLM agents — candidate pool + value dyna…☆205Updated this week
- 基于 Jingyun Studio + DeepSeek Harness (DSH) 打 造的一站式 AI 商业化桌面客户端，一个将 AI 智能体 / 技能 / 工作流转化为可交易商品的完整商业化平台客户端。 井云为 DSH 注入了完整的商业闭环：登录注册 → 会员体系 →…☆1,007Sep 30, 2026Updated 2 weeks ago
- We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.☆512Updated this week
- [NeurIPS 2026] State of Thought Enables Endogenous Reasoning☆163Oct 6, 2026Updated last week
- Pluggable controls for reliable AI agents: validated outputs, bounded loops and frozen collective decisions.☆145Updated this week
- An end-to-end growth tool that understands the product, fetch the data it needs, researches the market, executes campaigns, and reviews r…☆1,992Sep 28, 2026Updated 2 weeks ago