1-bit inference of 0.8M param GPT running inside 8192 bytes of sram(twitter.com)
twitter.com
1-bit inference of 0.8M param GPT running inside 8192 bytes of sram
https://twitter.com/monty10x/status/2043399937073754117
0 コメント
—
https://twitter.com/monty10x/status/2043399937073754117
—