Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
Articole: 8
-
Banning specific whole-phrases in a sequence
-
Swordfish, a Weight-Quantized GEMM Family for NVIDIA Blackwell
-
Aggressive decode optimizations for Qwen3-0.6B on an RTX 5090 GPU
-
Implementing Tiktoken in C, with SIMD
-
Implementing Google’s SentencePiece in C with aggressive optimizations
-
A step-by-step tutorial on building a production Top-K CUDA kernel.
-
Concise mapping of PyTorch op schema notation to idiomatic C++ signatures.
-
Learning Vulkan compute shaders the hard way: from assuming ‘device and queue = basically home’ to understanding why the compiler won’t hold your hand.