George Hotz 6960bcded0 back to 6.54GB for stable diffusion (#2288) ... * back to 6.54GB for stable diffusion * cleanups * only outputs, not inputs * err, restore hack for world		2023-11-13 16:50:04 -08:00
..
codegen	get_linearizer_actions does not return illegal actions (#2287)	2023-11-13 11:48:54 -05:00
features	bad hotfix for optimize_local_size, try again	2023-11-12 10:41:11 -08:00
nn	Stable diffusion WebGPU port (#1370)	2023-11-03 18:29:16 -07:00
renderer	refactor/ci: delete many `# type: ignore` (#2281)	2023-11-12 11:04:20 -08:00
runtime	back to 6.54GB for stable diffusion (#2288)	2023-11-13 16:50:04 -08:00
shape	examples of new GPT2 and JIT change (#2261)	2023-11-10 15:07:02 -05:00
graph.py	refactor/ci: delete many `# type: ignore` (#2281)	2023-11-12 11:04:20 -08:00
helpers.py	proper wmma (#2245)	2023-11-09 15:15:18 -08:00
jit.py	back to 6.54GB for stable diffusion (#2288)	2023-11-13 16:50:04 -08:00
lazy.py	refactor/ci: delete many `# type: ignore` (#2281)	2023-11-12 11:04:20 -08:00
mlops.py	add mops to graph, refactor IMAGE (#2100)	2023-10-17 21:27:51 -07:00
ops.py	hotfix mypy	2023-11-10 15:43:30 -08:00
realize.py	examples of new GPT2 and JIT change (#2261)	2023-11-10 15:07:02 -05:00
tensor.py	add dilation to avg_pool2d (#2270)	2023-11-13 08:47:56 -08:00