Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
-
Some time ago, I explored using CuteDSL to write some kernels for vLLM to enjoy the JIT benefits (ability to specialize on more parameters, don’t need to recompile vLLM from source during development, etc…).
-
tcgen05 is the set of PTX instructions to program Tensor Cores on the latest NVIDIA Blackwell GPUs (sm100, not to be confused with consumer Blackwell sm120).
-
Last month, I participated in the AMD Distributed Challenge, hosted by GPU MODE.
-
Recently I tweeted about realistic Speed-of-Light (SOL) of 5090 and RTX PRO 6000 for some dtypes, and mobicham asked me about FP8 MMA with FP16 accumulation.
-
In this post, I will walkthrough how I learned to implement Flash Attention for 5090 in CUDA C++.