{"author":"chenyu","author_email":"chenyu@fastmail.com","author_time":1704337002,"commit_time":1704391942,"committer":"chenyu","committer_email":"chenyu@fastmail.com","hash":"ab7dfd637b31695bc332b76254f98dac4ead4b68","message":"use float for acc dtype for half tensor sum\n\nwe previously only upcast uint and int, and half was using half for acc.\nchange to acc in float for precision. but cast the result back to half to match torch/jax output dtype\n","parents":["6fa285b94360d1b8d2f380e5f8a70e6c92d8348d"],"tree_hash":"904eebb1ac69d8bfc5fc1e936a52387fc37ead2e"}