vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-28 11:49:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Update DeepSeek-V3-Chat-multi-gpu-marlin.yaml

Browse source
This commit is contained in:
Atream 2025-02-26 21:53:50 +08:00 • committed by GitHub
parent 9660b2cc1e
commit 90eb87b3fc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-multi-gpu-marlin.yaml
View file

@ -168,5 +168,5 @@
replace:
class: "default"
kwargs:
generate_device: "cuda:0"
prefill_device: "cuda:0"
generate_device: "cuda:1"
prefill_device: "cuda:1"