Khushbu Agarwal e10a11323a Fix quant scale matrix layout for block scale gemm (#3079) ...

* Adding support for TiledPermuteN

* Adding test

* moving shuffle functions to common place

* resolving commit hook

* fix formatting

[ROCm/composable_kernel commit: b11f53a484]

2025-10-27 13:56:07 -07:00

..

reference

[CK_TILE] Add conv fwd + bias + clamp example (#3012)

2025-10-27 18:43:09 +01:00

arg_parser.hpp

…

check_err.hpp

[CK_TILE] Patch for pk_fp4 ref check and buffer load. (#3044)

2025-10-20 14:47:04 +08:00

concat.hpp

…

convolution_host_tensor_descriptor_helper.hpp

…

convolution_parameter.hpp

…

device_memory.hpp

…

device_prop.hpp

…

fill.hpp

[CK_TILE] Refine pk_fp4's fill, pack, and unpack (#2845)

2025-09-17 10:54:06 +08:00

flush_icache.hpp

docs: add inline comments about flush_cache and rotating buffer

2025-10-17 12:56:47 -04:00

hip_check_error.hpp

…

host_tensor.hpp

…

joinable_thread.hpp

…

kernel_launch.hpp

…

permute_pk_int4.hpp

…

ranges.hpp

…

rotating_buffers.hpp

limit the rotating count to prevent oom (#3087)

2025-10-24 08:55:34 -07:00

stream_config.hpp

…

stream_utils.hpp

…

tensor_shuffle_utils.hpp

Fix quant scale matrix layout for block scale gemm (#3079)

2025-10-27 13:56:07 -07:00

timer.hpp

…