Hackernews posts about Blackwell

1. Nvidia doubles RTX PRO 6000 Blackwell's MSRP to a staggering $16,000 (www.tomshardware.com)
   37 points by jacquesm 2 days ago | 18 comments
2. Characterizing Warp Divergence from Pascal to Blackwell (arxiv.org)
   27 points by matt_d 16 days ago | 1 comments
3. Nvidia Vera Rubin NVL72 measured to have 10x TPS per megawatt than Blackwell (twitter.com)
   4 points by andy12_ 24 days ago | discuss
4. China's Moonshot AI reportedly used Nvidia Blackwell chips for training Kimi K3 (www.tomshardware.com)
   3 points by rndsignals 17 days ago | discuss
5. Nvidia Vera Rubin NVL72 on CoreWeave 10x More Tokens per Megawatt Than Blackwell (www.coreweave.com)
   3 points by EvgeniyZh 24 days ago | discuss
6. Spec Sheets Are Not Kernels: INT8 Availability on Nvidia Blackwell Ultra (arxiv.org)
   2 points by Jimmc414 2 days ago | discuss
7. Optimizing an NVFP4 Blockscaled GEMM on RTX Pro 6000 Blackwell GPU (SM120) (research.colfax-intl.com)
   2 points by matt_d 5 days ago | discuss
8. Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials (discoveredmaterials.com)
   160 points by advaith08 3 days ago | 35 comments
9. 15 years of FP64 segmentation, and why the Blackwell Ultra breaks the pattern (nicolasdickenmann.com)
   202 points by fp64enjoyer 6 months ago | 80 comments
10. Nvidia has produced the first Blackwell wafer on US soil (www.xda-developers.com)
    164 points by kristianp 10 months ago | 64 comments
11. Blackwell: Nvidia's GPU (chipsandcheese.com)
    112 points by pella about 1 year ago | 31 comments
12. Nvidia Blackwell GeForce RTX 50 Series Opens New World of AI Computer Graphics (nvidianews.nvidia.com)
    76 points by OnlineInference over 1 year ago | 23 comments
13. Writing high-performance matrix multiplication kernels for Blackwell (docs.jax.dev)
    63 points by lairv 11 months ago | 6 comments
14. SVDQuant+NVFP4: 4× Smaller, 3× Faster FLUX with 16-bit Quality on Blackwell GPUs (hanlab.mit.edu)
    52 points by lmxyy over 1 year ago | 10 comments
15. 4× RTX Pro 6000 Blackwell on Water, and the One Card That Wouldn't Behave (sabareesh.com)
    45 points by sabareesh 2 months ago | 53 comments
16. Apple's rumored M7 Ultra targets 1.5TB and Blackwell-class AI performance (www.tomshardware.com)
    26 points by rbanffy about 1 month ago | 31 comments
17. Matmul on Blackwell: Part 2 – Using Hardware Features to Optimize Matmul (www.modular.com)
    23 points by robertvc 11 months ago | 13 comments
18. AMD launches AI chip to rival Nvidia's Blackwell (www.cnbc.com)
    20 points by teleforce almost 2 years ago | discuss
19. Nvidia Puts Grace Blackwell on Every Desk and at Every AI Developer's Fingertips (nvidianews.nvidia.com)
    11 points by TiredOfLife over 1 year ago | 4 comments
20. Nvidia Unveils Rubin CPX Amidst Chart-Topping Blackwell Ultra MLPerf Results (hothardware.com)
    11 points by rbanffy 11 months ago | discuss
21. Nvidia RTX Blackwell GPU Architecture [pdf] (images.nvidia.com)
    10 points by ydnyshhh over 1 year ago | discuss
22. Nvidia DGX Station – The GB300 Grace Blackwell 748 GB VRAM Workstation (www.nvidia.com)
    9 points by car 5 months ago | 4 comments
23. Nvidia and TSMC Celebrate First Nvidia Blackwell Wafer Produced in the US (blogs.nvidia.com)
    9 points by jonbaer 10 months ago | 1 comments
24. Blackwell: Nvidia's GPU (old.chipsandcheese.com)
    9 points by mfiguiere about 1 year ago | 1 comments
25. Nvidia raises RTX Pro 6000 Blackwell GPU pricing to $13,250 (www.tomshardware.com)
    9 points by adam_rida 2 months ago | discuss
26. Nvidia Blackwell Ultra (GB300): -97% INT8/FP64,+50% FP4 Dense,+55% VRAM,+114% At (resources.nvidia.com)
    8 points by Sweepi 12 months ago | 3 comments
27. Nvidia Blackwell Delivers World-Record DeepSeek-R1 Inference Performance (developer.nvidia.com)
    8 points by daviducolo over 1 year ago | discuss
28. AI inference costs dropped up to 10x on Nvidia's Blackwell (venturebeat.com)
    7 points by CrankyBear 6 months ago | 3 comments
29. WarpSpeed Approaches Speed of Light on Blackwell (www.doubleai.com)
    7 points by laginimaineb 3 months ago | 1 comments
30. Performant C/CUDA inference engine for Qwen 3.6 35B on RTX 5090 / Blackwell (github.com)
    6 points by ambuds about 1 month ago | 1 comments
31. Nvidia Tensor Core Evolution: From Volta to Blackwell (semianalysis.com)
    6 points by pella about 1 year ago | discuss
32. NVIDIA to Manufacture Blackwell AI Supercomputers in US for First Time (blogs.nvidia.com)
    6 points by walterbell over 1 year ago | discuss
33. Nvidia announces $3000 128gb Blackwell desktop GPU/CPU mini super computer (nvidianews.nvidia.com)
    5 points by h_tbob over 1 year ago | 2 comments
34. Nvidia GPU: Discussing Blackwell's Limitations and Predicting Rubin (github.com)
    5 points by yankcrime 7 months ago | discuss
35. We rebuilt MXFP8 MoE kernels from scratch to run 3.5x faster on Blackwell (cursor.com)
    5 points by ecz 12 months ago | discuss
36. 384GB Personal AI Workstation with Four Nvidia RTX 6000 Pro Blackwell Max-Q GPUs (a16z.com)
    4 points by transpute 12 months ago | 2 comments
37. Guess-Verify-Refine: Data-Aware Top-K for Sparse-Attention Decoding on Blackwell (arxiv.org)
    4 points by matt_d 4 months ago | 1 comments
38. Nvidia Blackwell Ultra: The Chip Powering the AI Factory Era (developer.nvidia.com)
    4 points by ksec 12 months ago | 1 comments