Triton ã¨ã¯ Tritonã¯ã2021å¹´ã«OpenAIããªãªã¼ã¹ããã½ããã¦ã§ã¢ã§ããªãªã¼ã¹è¨äºæ°ã以ä¸ã®ãããªç¹å¾´ãããã¾ãã an open-source Python-like programming language which enables researchers with no CUDA experience to write highly efficient GPU codeâmost of the time on par with what an expert would be able to produce. (翻訳) ãªã¼ãã³ã½ã¼ã¹ã®Python風ããã°ã©ãã³ã°è¨èªã§ãCUDAã®çµé¨ããªãç ç©¶è ã§ããå¤ãã®å ´åå°éå®¶ã¨åçã®å¹çã§GPUåãã³ã¼ããè¨è¿°ã§ããããã«è¨è¨ããã¦ããã Tritonã¯ãã¿ã¤ã«ï¼Tileï¼ ã¾ã㯠ãããã¯ï¼Blockï¼ ã¨å¼ã°ãããã¼


{{#tags}}- {{label}}
{{/tags}}