Hackernews posts about A100s

  1. Show HN: I embedded 685M public texts in 32 minutes (on 8x A100, Rust, TensorRT) (github.com)
    7 points by ddayanov 17 days ago | discuss
  2. Profile(v2.1.4) physics-aware optimizer for vLLM (31→470 tok/s on A100) (github.com)
    3 points by jungledesh 3 days ago | discuss
  3. Giant Banana Pulled Over: Driver Says Cops Have Stopped Him 100s of Times (cowboystatedaily.com)
    8 points by speckx 1 day ago | 1 comments
  4. Cohere Open-Sources Command A+, a 218B Moe Model That Runs on Two H100s (firethering.com)
    4 points by steveharing1 30 days ago | discuss
  5. Air Canada Captain Arrested for Flying 100s of Flights Without Required License (viewfromthewing.com)
    2 points by crescit_eundo 12 days ago | discuss
  6. Show HN: Lean bulk, cut, body recomp. Calculate maintenance calories (macrocodex.app)
    27 points by faangguyindia about 23 hours ago | 9 comments
  7. Bare metal A100s for $0.38/HR (aggregating idle capacity) (neocloudx.com)
    15 points by zyzzxroad 6 months ago | discuss
  8. Rendering attractors at 200 megapixels on A100s (axisophy.com)
    3 points by scylx 4 months ago | 1 comments
  9. A100s are more cost-efficient than H100s for small training tasks (cloudbreakr.substack.com)
    3 points by jack_nclx 6 months ago | 1 comments
  10. Show HN: Terminal-Bench-RL: Training long-horizon terminal agents with RL (github.com)
    125 points by Danau5tin 11 months ago | 12 comments
  11. Show HN: A GPU group-buying layer to get enterprise rates (~50% off H100s) (trysaga.ai)
    5 points by DdotR over 1 year ago | discuss
  12. Show HN: Mixlayer – code and deploy LLM prompts using JavaScript (www.mixlayer.com)
    5 points by zackangelo over 1 year ago | discuss
  13. Ask HN: How long before we get "coding agent in a box"?
    2 points by heavyarms 6 months ago | 3 comments
  14. Fireworks AI – Charging $192 for less than $0.20 of Training Cost
    2 points by mountainriver 9 months ago | discuss
  15. Show HN: Airbnb for GPUs (www.gpudeploy.com)
    2 points by lschneider almost 2 years ago | discuss
  16. Show HN: I built a CLI to arbitrage GPU prices across 10 clouds (pypi.org)
    1 points by Facingsouth 4 months ago | discuss
  17. Benchmark: A100 vs. H100 NVMe Random Read throughput during multi-GPU loading
    1 points by pveldandi 6 months ago | discuss
  18. Show HN: Free Tools for Tabs, Chords, Lyrics Use 8 A100 GPUs (lamucal.com)
    30 points by CMLab almost 2 years ago | 5 comments
  19. Nvidia Data Center GPUs Explained: From A100 to B200 and Beyond (www.bentoml.com)
    4 points by bbzjk7 10 months ago | discuss
  20. The Blackmarket for Nvidia H100, A100 AI GPUs Is Exploding (www.techradar.com)
    4 points by pwmtr almost 2 years ago | discuss
  21. Does an A100 still make profit (a100economics.com)
    3 points by ramoz 7 months ago | 1 comments
  22. Show HN: IgniteMS – batch text embeddings at 253K msg/s on 8x A100 (github.com)
    3 points by ddayanov about 1 month ago | discuss
  23. A100 is a puzzle game inspired by the mobile game „1010 " by Gram Games (cobour.itch.io)
    3 points by doener 12 months ago | discuss
  24. Chinese team build optical chip AI that is 100x faster than Nvidia's A100 chip (www.scmp.com)
    2 points by didizaja 6 months ago | 1 comments
  25. Story of Two GPUs: Characterizing the Resilience of Hopper H100 and Ampere A100 (arxiv.org)
    2 points by rbanffy about 2 months ago | discuss
  26. A100 is better than H100 according to exIT Technologies (exittechnologies.com)
    2 points by p1esk almost 2 years ago | discuss
  27. GPU telemetry anomaly: 146W idle draw on A100 (white paper) (github.com)
    1 points by mikebains about 1 month ago | discuss
  28. Show HN: Turn a text prompt into an interactive world, with just one A100 (mattqlf25--ephemeral-web.modal.run)
    1 points by qflop 4 months ago | discuss
  29. 2025 GPU Price A100 and H100 Cloud Pricing and Availability (cast.ai)
    1 points by Rainniis 8 months ago | discuss
  30. Summarizing sales calls using PostgreSQL, Llama 3.1, A100 GPU (www.thenile.dev)
    1 points by code_reader over 1 year ago | discuss
  31. Summarizing sales calls using Llama 3.1, A100 GPU and Postgres (www.thenile.dev)
    1 points by infra_dev over 1 year ago | discuss
  32. Show HN: Voice bots with 500ms response times (fastvoiceagent.cerebrium.ai)
    315 points by kwindla almost 2 years ago | 99 comments
  33. Show HN: ZSE – Open-source LLM inference engine with 3.9s cold starts (github.com)
    58 points by zyoralabs 4 months ago | 9 comments
  34. Launch HN: Cerebrium (YC W22) – Serverless Infrastructure Platform for ML/AI
    48 points by za_mike157 almost 2 years ago | 32 comments
  35. Show HN: Per-instance TSP Solver with No Pre-training (1.66% gap on d1291)
    21 points by jivaprime 6 months ago | 5 comments
  36. Show HN: LeetGPU – LeetCode for GPU Programming (leetgpu.com)
    9 points by kmans over 1 year ago | discuss