Logo
Explore Help
Register Sign In
ROCm/composable_kernel
1
0
Fork 0
You've already forked composable_kernel
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-07-03 05:37:34 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
3ee220aba954a52d7a425d9e95a667a94b67e33d
composable_kernel/include/ck_tile/host/reference
History
carlushuang c0adab4850 [CK_TILE] moe sorting ex kernel to support expert > 128 (#1840)
* moe sorting ex

* fix bug for race condition

* fix bug and optimze large expert

* fix

* optimize with sub_token_oneshot

* support skip empty tokens for expert sorting

* update moe_sorting

* tidy code
2025-02-11 17:49:17 +08:00
..
reference_batched_dropout.hpp
…
reference_batched_elementwise.hpp
…
reference_batched_gemm.hpp
…
reference_batched_masking.hpp
…
reference_batched_rotary_position_embedding.hpp
…
reference_batched_softmax.hpp
…
reference_batched_transpose.hpp
…
reference_elementwise.hpp
…
reference_fused_moe.hpp
…
reference_gemm.hpp
…
reference_im2col.hpp
…
reference_layernorm2d_fwd.hpp
…
reference_moe_sorting.hpp
…
reference_permute.hpp
…
reference_reduce.hpp
…
reference_rmsnorm2d_fwd.hpp
…
reference_rowwise_quantization2d.hpp
…
reference_softmax.hpp
…
reference_topk.hpp
…
Powered by Gitea Version: 1.25.4 Page: 2366ms Template: 9ms
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API