Asynchronous Error Handling Is Hard
11 by hedgehog | 1 comments on Hacker News.
World News - Find latest world news and headlines today based on politics, crime, entertainment, sports, lifestyle, technology and many
Monday, 30 June 2025
Sunday, 29 June 2025
New top story on Hacker News: Show HN: A tool to benchmark LLM APIs (OpenAI, Claude, local/self-hosted)
Show HN: A tool to benchmark LLM APIs (OpenAI, Claude, local/self-hosted)
3 by mrqjr | 1 comments on Hacker News.
I recently built a small open-source tool to benchmark different LLM API endpoints — including OpenAI, Claude, and self-hosted models (like llama.cpp). It runs a configurable number of test requests and reports two key metrics: • First-token latency (ms): How long it takes for the first token to appear • Output speed (tokens/sec): Overall output fluency Demo: https://llmapitest.com/ Code: https://ift.tt/Zyr32Rs The goal is to provide a simple, visual, and reproducible way to evaluate performance across different LLM providers, including the growing number of third-party “proxy” or “cheap LLM API” services. It supports: • OpenAI-compatible APIs (official + proxies) • Claude (via Anthropic) • Local endpoints (custom/self-hosted) You can also self-host it with docker-compose. Config is clean, adding a new provider only requires a simple plugin-style addition. Would love feedback, PRs, or even test reports from APIs you’re using. Especially interested in how some lesser-known services compare.
3 by mrqjr | 1 comments on Hacker News.
I recently built a small open-source tool to benchmark different LLM API endpoints — including OpenAI, Claude, and self-hosted models (like llama.cpp). It runs a configurable number of test requests and reports two key metrics: • First-token latency (ms): How long it takes for the first token to appear • Output speed (tokens/sec): Overall output fluency Demo: https://llmapitest.com/ Code: https://ift.tt/Zyr32Rs The goal is to provide a simple, visual, and reproducible way to evaluate performance across different LLM providers, including the growing number of third-party “proxy” or “cheap LLM API” services. It supports: • OpenAI-compatible APIs (official + proxies) • Claude (via Anthropic) • Local endpoints (custom/self-hosted) You can also self-host it with docker-compose. Config is clean, adding a new provider only requires a simple plugin-style addition. Would love feedback, PRs, or even test reports from APIs you’re using. Especially interested in how some lesser-known services compare.
Saturday, 28 June 2025
Friday, 27 June 2025
Robert F. Kennedy Jr. Tells Fox News The Rotten Truth About His Anti-Fluoride Crusade
from Yahoo News - Latest News & Headlines https://ift.tt/EBTqe4L
Thursday, 26 June 2025
Jill Biden's 'work husband' runs for cover as privilege protection crumbles
from Yahoo News - Latest News & Headlines https://ift.tt/zIqGN3s
Wednesday, 25 June 2025
Tuesday, 24 June 2025
New top story on Hacker News: Nvidia's RTX 5050 GPU starts at $249 with last-gen GDDR6 VRAM
Nvidia's RTX 5050 GPU starts at $249 with last-gen GDDR6 VRAM
16 by microsoftedging | 16 comments on Hacker News.
16 by microsoftedging | 16 comments on Hacker News.
Monday, 23 June 2025
Fart walking — do this 10-minute indoor walking workout immediately after eating to lower your blood sugar, aid weight loss
from Yahoo News - Latest News & Headlines https://ift.tt/ThlSu1B
Subscribe to:
Posts (Atom)