Viewing profile — technoabsurdist

hi I work at wafer. yes we ran benchmarks. for example our Kimi K3 is live on open router and in order to host there you have to run accuracy checks. like tau/gpqa. and then u must…

sounds good feedback taken, thanks beffjezos

hi yes it’s not optimized for single stream it’s optimized for total node throughput

this is exactly our thesis at wafer :) thank you for the support

AMD MI355X uses 1,400W per GPU and NVIDIA B200 uses 1,200W. So AMD uses about 16% more power.

yes it is 213 tok/s single stream (so per user)

hi i work at wafer. no the margins are lower averaging at about ~40%. utilization is one of the highest order bits in determining margins here, yes.

Hi HN, I’m Emilio. We’re launching the Wafer extension for the popular IDEs (VS Code, Cursor and Antigravity). Wafer exists to make performance engineers more efficient. Most of th…

Hey HN! We're building a profiler for ML inference that actually shows what's happening at the hardware level without having to manually parse through flame graphs, or set up nsys …

If you've ever tried to profile PyTorch or other Python code, you know that it can be painful to setup right. Nsight profiler is great, but it feels like using a sledgehammer to ha…

^ We currently just have llama3.1-8b, so we'll be working on adding more models across more hardware options!

We just launched Chip Benchmark, an open-source tool for hardware-centric benchmarking of open-weight LLMs across accelerators like NVIDIA A100/H100/L40S and AMD MI300X. It measure…

We've been doing lots of GPU kernel profiling and optimization on cloud infrastructure, but without local GPU hardware, that meant constant SSH juggling: upload code, compile remot…

We've been doing lots of GPU kernel profiling and optimization on cloud infrastructure, but without local GPU hardware, that meant constant SSH juggling: upload code, compile remot…

We built Chisel to make GPU kernel profiling hardware-free. It lets you run chisel profile kernel.cu and get full Nsight/Ncompute or rocprofv3 reports without a GPU needed. It spin…

oh yeah, in my experience anything below ROCm6.x really sucks. I tried to run qwen2.5-32B on ROCm5.x and it was running at Have you tried running any sort of LLM inference on your …

^ title. I've been renting MI300Xs coz they are cheaper than H100s and my experience has been generally OK (smoother than i expected based on people shitting on AMD so much online)…

We've been running lots of experiments on AMD MI300Xs. The price/performance is compelling compared to NVIDIA, and ROCm is finally usable. But, no local hardware means constant SSH…

We've been running lots of AMD MI300X experiments lately. The price/performance is compelling compared to NVIDIA, and ROCm keeps getting better. But, no local AMD hardware means co…

correct github link: https://github.com/Herdora/chisel