开发者工具1 week ago
WatchMachineGo
实时可视化硬件在运行LLM推理时的性能指标
dev_dan_2 · HN
WatchMachineGo – A visualizer to show hardware performing LLM inference
完整作品展
技术栈
21 projects
实时可视化硬件在运行LLM推理时的性能指标
dev_dan_2 · HN
WatchMachineGo – A visualizer to show hardware performing LLM inference
用NVIDIA TensorRT-LLM在消费级GPU上进行高性能大语言模型推理。
brianhabana123 · HN
TensorRT-LLM running natively on Windows (no WSL)
对比和评估 AI 模型在编码、推理、代理和其他基准测试中的表现。
davidtsong · HN
Benchmarklist: track AI benchmarks (2.4k+), models, and capabilities
微调LLM、清理数据集，教授和删除自定义事实，获得密码学删除证明。
@MBrew26730 · X
Dataset cleaning + fine tuning + continual learning at
查找与您硬件兼容的AI模型并查看性能和价格估计。
cdnsteve · HN
Tokenstead, find AI models for your hardware
压缩提示词并检测重复工具调用，降低LLM代币成本
@DeveloperL92487 · X
I built my first app in 60min And now I got $500 MRR in one month Check here if you are interested It’s a tool to reduce agent token consumption, speed up agent response, and clean up memory cache
监控AI应用中的模型调用、代理步骤和检索，追踪令牌、成本和延迟。
ephraimduncan · HN
Observability for Coding Agents and LLM Applications
压缩LLM提示词和文档以降低token使用和API成本
@marcusyul · X
THEY JUST GAVE AWAY 100 MILLION FREE TOKENS SO YOU CAN STOP BURNING THROUGH YOUR CLAUDE CODE BUDGET. if you code with AI you already know: the session fills up, starts failing, and on top of that you're overpaying there's a tool that fixes this: it shrinks the context before the model even sees it same model, same response, a fraction of the cost in a real session: from $154 to $43. a 72% drop and right now: → extend your Fable sessions in Claude Code → 100M free tokens to try it out you don't switch models you don't touch your code you just stop paying to repeat yourself link below ⬇️
在 leaderboard 上按官方基准对比 AI 大模型的性能排名
fcten · V2EX
做了一个大模型 leaderboard 网站 最近一个月 CodeX 疯狂送重置，token 根本用不完，顺手做点东西。 地址：[知行录]( https://leaderboard.cn/) 排行依据主要为模型官方基准测试成绩。非主观排名。 数据会持续更新。如果有点用，欢迎各位 v 友收藏～
对比 AI 模型在编码任务上的表现,支持成本追踪和 ELO 排名。
@intheworldofai · X
On the World of AI Bench (vibe-coding composite): Claude Fable 5 → 85.2 GPT-5.6-sol → 82.4 kimi-k3 → 81.5 Moonshot’s K3 just walked in and claimed bronze on one of the toughest coding-focused leaderboards out there.
在 Enclave 保密计算平台上运行的 LLM 聊天界面。
SteveDeFacto · HN
Hi HN, I built Enclave, self-serve confidential compute on GPUs. Technical documentation is on the site, but I'd rather show than tell. Here are a couple apps hosted live on the platform: LLM Chat bot: https://cc1f4f3f.app.enclave.host AI Image Generation: https://da09d0f2.app.enclave.host If you have any questions, I would be more than happy to discuss.
将 100 多个来源的 AI/LLM 新闻汇总成每日摘要线程。
jonam21 · HN
KBlip – turns AI/LLM news across 100 sources into daily digest threads