vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-09 05:54:06 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update triton_attention.py

Browse source
This commit is contained in:
Atream 2025-02-15 15:41:01 +08:00 • committed by GitHub
parent 1548c99234
commit d90749d35d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 7 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ktransformers/operators/triton_attention.py
View file

@ -1,3 +1,9 @@
# Adapted from
# https://github.com/sgl-project/sglang/blob/9f635ea50de920aa507f486daafba26a5b837574/python/sglang/srt/layers/attention/triton_ops/decode_attention.py
# which was originally adapted from
# https://github.com/ModelTC/lightllm/blob/96353e868a840db4d103138caf15ed9dbea8c186/lightllm/models/deepseek2/triton_kernel/gqa_flash_decoding_stage1.py
# https://github.com/ModelTC/lightllm/blob/96353e868a840db4d103138caf15ed9dbea8c186/lightllm/models/deepseek2/triton_kernel/gqa_flash_decoding_stage2.py
import triton import triton
import triton.language as tl import triton.language as tl