George HotzandGitHub d58586bb17 safetensors! (#903) ...

* safetensors test

* safe_save

* load back with real safetensors

* bugfix in device name. add simple torch_load

* it works for llama, but it's slower...

* mmap

* no intermediate

* load mmaped

* readinto speed

* not ready yet

* revert that

2023-06-02 13:41:09 -07:00

..

lib.py

support Int64 type in cstyle gen (#860)

2023-05-30 16:04:46 -07:00

ops_clang.py

support Int64 type in cstyle gen (#860)

2023-05-30 16:04:46 -07:00

ops_cpu.py

Disktensors! (#819)

2023-05-28 15:40:37 -07:00

ops_cuda.py

Fix cuda (#836)

2023-05-29 07:59:36 -07:00

ops_disk.py

safetensors! (#903)

2023-06-02 13:41:09 -07:00

ops_gpu.py

support Int64 type in cstyle gen (#860)

2023-05-30 16:04:46 -07:00

ops_llvm.py

linearizer! (#714)

2023-03-19 23:43:49 -07:00

ops_metal.py

support Int64 type in cstyle gen (#860)

2023-05-30 16:04:46 -07:00

ops_torch.py

Onnx ops And, Or, Xor, Not (#847)

2023-05-29 11:09:20 -07:00