9 Commits

Author	SHA1	Message	Date
Sam Gross	7588893ce2	Some additional clean-ups (#5505) ... - Remove some uses of mega-header THP.h - Use HANDLE_TH_ERRORS in functions that may throw - Move NumPy includes to common header - Delete unused allocator	2018-03-05 17:45:02 -05:00
Adam Paszke	9f685e4aa3	Ensure GIL is held in ObjectPtrAllocators (#2581)	2017-09-01 00:30:09 -04:00
Edward Z. Yang	6b69723d4f	Document how Numpy memory management works. ... Signed-off-by: Edward Z. Yang <ezyang@fb.com>	2017-07-20 10:55:35 -04:00
Soumith Chintala	1e98155711	long ->size_t	2017-07-13 02:40:44 -04:00
Soumith Chintala	1c14178c65	fix osx compilation	2017-07-13 02:38:56 -04:00
João Felipe Santos	2abbb5133c	Fixing function signatures: long -> ptrdiff_t (#1232)	2017-04-11 11:37:21 -07:00
Adam Paszke	f531d98341	Fix memory leak in torch.from_numpy	2017-03-12 13:31:32 -04:00
Sam Gross	bb72ccf1a5	Support CUDA IPC in Python 3 (#203) ... CUDA IPC only works with Python 3 using the "spawn" start method. You can select the start method using the get_context method: import torch.multiprocessing as mp ctx = mp.get_context('spawn') queue = ctx.Queue() event = ctx.Event()	2016-12-19 20:42:53 -05:00
Adam Paszke	f9d186d33a	Add initial version of multiprocessing module	2016-08-31 19:46:08 -07:00