Skip to content

Commit 482b3fd

Browse files
authored
misc: update cuda merge_attn_states kernel (#276)
* misc: add cuda merge_attn_states kernel index * misc: add cuda merge_attn_states kernel index * misc: add cuda merge_attn_states kernel index
1 parent b9f430f commit 482b3fd

File tree

3 files changed

+176
-42
lines changed

3 files changed

+176
-42
lines changed

README.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -307,6 +307,7 @@ The kernels listed here will guide you through a step-by-step progression, rangi
307307
| ✔️ [rms_norm_f16x8_pack_f32](./kernels/rms-norm/rms_norm.cu)|f16|f32|[link](./kernels/rms-norm/)|⭐️⭐️|
308308
| ✔️ [rms_norm_f16_f32](./kernels/rms-norm/rms_norm.cu)|f16|f32|[link](./kernels/rms-norm/)|⭐️⭐️|
309309
| ✔️ [nms_f32](./kernels/nms/nms.cu)|f32|/|[link](./kernels/nms)|⭐️⭐️|
310+
| ✔️ [merge_attn_states](./kernels/openai-triton/merge-attn-states/cuda_merge_attn_states.cu)|f16/bf16/f32|f32|[link](./kernels/openai-triton/merge-attn-states)|⭐️⭐️|
310311
| ✔️ [notes v1(deprecated)](./kernels/notes-v1.cu)|f32|f32|/|⭐️⭐️|
311312
| ✔️ [How to use nsys/ncu(timeline/ptx/sass)](./kernels/nvidia-nsight/)|/|/|[link](./kernels/nvidia-nsight/)|⭐️⭐️|
312313

0 commit comments

Comments
 (0)