Hackernews posts about H100s

  1. vLLM Serving Experiments on H100s – config beats the baseline on p95 TTFT,ITL (efficientagent.substack.com)
    1 points by bnayak25 11 days ago | discuss
  2. Launch HN: machine0 (YC S26) – Persistent CPU and GPU VMs from the CLI (machine0.io)
    81 points by bwm 3 days ago | 44 comments
  3. Ask HN: You have model orders of magnitudes faster than transformer, so?
    1 points by aunekiaru 6 days ago | discuss
  4. Show HN: ExANS – Lossless KV cache compression at 622 GB/s on H100 (www.theopenlake.com)
    15 points by arnav__1 16 days ago | discuss
  5. Proving Muse Glimmer in Zero-Knowledge at 85 Tok/S on an H100 (attestable.com)
    4 points by mildog8 10 days ago | discuss
  6. See how an H100 works in 3D with threejs (gpu.kylejeong.com)
    3 points by Kylejeong21 5 days ago | discuss
  7. Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it (www.ctgt.ai)
    170 points by cgorlla 22 days ago | 73 comments
  8. Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials (discoveredmaterials.com)
    161 points by advaith08 9 days ago | 36 comments
  9. Launch HN: Stoa Markets (YC S26) – A Marketplace for GPUs and AI Servers (www.stoaexchange.com)
    77 points by erenberke 11 days ago | 51 comments
  10. Show HN: Cuts Long Horizon Inference Costs by 50% via external KV Cache Offload (github.com)
    22 points by arnav__1 26 days ago | discuss
  11. Show HN: I built a hypervisor and client for inference on consumer compute (scalattice.com)
    3 points by RomulusHill 26 days ago | discuss
  12. Show HN: Open OneNote Viewer in Rust (github.com)
    3 points by emsi 19 days ago | discuss
  13. $2 H100s: How the GPU Rental Bubble Burst (www.latent.space)
    403 points by swyx almost 2 years ago | 279 comments
  14. Furiosa: 3.5x efficiency over H100s (furiosa.ai)
    212 points by written-beyond 7 months ago | 160 comments
  15. 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
  16. Cohere Open-Sources Command A+, a 218B Moe Model That Runs on Two H100s (firethering.com)
    4 points by steveharing1 3 months ago | discuss
  17. The "setup tax" on AWS H100s is killing iterative research
    3 points by miyamotomusashi 8 months ago | 2 comments
  18. Tracing tokens through Llama 3.1 8B inference on H100s (krithik.xyz)
    3 points by krithik_7 3 months ago | 1 comments
  19. A100s are more cost-efficient than H100s for small training tasks (cloudbreakr.substack.com)
    3 points by jack_nclx 8 months ago | 1 comments
  20. Scaling Coding-Agent RL to 32x H100s. 160% Improvement on Stanford's TBench (github.com)
    2 points by Danau5tin 10 months ago | 1 comments
  21. Free H100s for All .EDU User Emails (app.hyperbolic.xyz)
    2 points by hyperbolic_labs over 1 year ago | discuss
  22. CUDA Programming for Nvidia H100s (www.freecodecamp.org)
    1 points by eigenBasis 4 months ago | discuss
  23. Flux Fast: Making Flux Go Brrr on H100s (pytorch.org)
    1 points by sayak_paul_hf about 1 year ago | discuss
  24. Show HN: Terminal-Bench-RL: Training long-horizon terminal agents with RL (github.com)
    125 points by Danau5tin about 1 year ago | 12 comments
  25. Show HN: I built a website where you can easily fine-tune Llama 3.1 models (www.tunellama.com)
    8 points by hamadafm almost 2 years ago | 4 comments
  26. Ask HN: Is anyone using AMD GPUs for their AI workloads?
    6 points by technoabsurdist about 1 year ago | 2 comments
  27. Open-Source Inference is growing 10% week over week this year
    2 points by luew 4 months ago | 1 comments
  28. Ask HN: Where do you rent GPUs from?
    2 points by kd1996 5 months ago | discuss
  29. A claudeism that I want to confirm if anyone else is experiencing
    1 points by ramenprofitable 6 months ago | 1 comments
  30. Deploying DeepSeek on 96 H100 GPUs (lmsys.org)
    285 points by GabrielBianconi 12 months ago | 80 comments
  31. Processing Strings 109x Faster Than Nvidia on H100 (ashvardanian.com)
    216 points by ashvardanian 11 months ago | 26 comments
  32. Huawei's Ascend 910C delivers 60% of Nvidia H100 inference performance (www.tomshardware.com)
    118 points by sien over 1 year ago | 61 comments
  33. Exploring inference memory saturation effect: H100 vs. MI300x (dstack.ai)
    57 points by latchkey over 1 year ago | 12 comments
  34. Colossus AI Supercluster with over 100k Nvidia H100 GPUs (twitter.com)
    47 points by DeathArrow almost 2 years ago | 33 comments
  35. Processing Strings 109x Faster Than Nvidia on H100 (ashvardanian.com)
    34 points by samspenc 11 months ago | 3 comments
  36. How to train a model on 10k H100 GPUs? (soumith.ch)
    33 points by bobrenjc93 almost 2 years ago | discuss
  37. Dual RTX 5090 Beats $25,000 H100 in Real-World LLM Performance (www.hardware-corner.net)
    29 points by mdp2021 over 1 year ago | 12 comments
  38. Rent H100 SXMs for 0.99 (app.hyperbolic.xyz)
    10 points by hyperbolic_labs almost 2 years ago | 5 comments
  39. Ask HN: What is the cheapest ($/hour) H100 renting service with quick spin-up?
    10 points by dtquad almost 2 years ago | 4 comments
  40. Meta is using more than 100k Nvidia H100 AI GPUs to train Llama-4 (www.tomshardware.com)
    8 points by turtlegrids almost 2 years ago | 1 comments
  41. xAI's Colossus (100k H100 cluster) has begun training (twitter.com)
    7 points by famouswaffles almost 2 years ago | 1 comments
  42. H100 prices are melting *UP (www.latent.space)
    7 points by swyx 5 months ago | discuss