vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-28 20:00:06 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

add balance-serve, support concurrence

Browse source
This commit is contained in:
Atream 2025-03-31 22:55:32 +08:00
parent 8d0292aa44
commit 25cee5810e
196 changed files with 22077 additions and 565 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ktransformers/optimize/optimize_rules/DeepSeek-V2-Lite-Chat.yaml
View file

@ -22,7 +22,7 @@
replace:
class: ktransformers.operators.linear.KTransformersLinear
kwargs:
generate_device: "cpu"
generate_device: "cuda"
prefill_device: "cuda"
generate_op: "KLinearMarlin"
prefill_op: "KLinearTorch"