{"author":"chenyu","author_email":"chenyu@fastmail.com","author_time":1709606157,"commit_time":1709606157,"committer":"GitHub","committer_email":"noreply@github.com","hash":"957e9800f15bb3b8727f56b9298433432f703d9f","message":"llama + beam to mac benchmark, full cifar to nvidia benchmark (#3612)\n\nwould merge if it's also ~1 minute. btw why is gpt2 beam not slower in the first beam run?","parents":["282bbd5acbeff88a358f945de6acca07c0ec7c19"],"tree_hash":"c5ff2ed306394ded18d547e68f9a7a0863b442f6"}