Merge pull request #697 from kvcache-ai/fix-yaml

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

Merge pull request #697 from kvcache-ai/fix-yaml
Update DeepSeek-V3-Chat-multi-gpu-marlin.yaml
9650893a · Atream · GitHub · 9660b2cc · 90eb87b3 · 9650893a
Unverified Commit 9650893a authored Feb 26, 2025 by Atream Committed by GitHub Feb 26, 2025
Hide whitespace changes
Inline Side-by-side

Showing with 2 additions and 2 deletions

ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-multi-gpu-marlin.yaml ...ize/optimize_rules/DeepSeek-V3-Chat-multi-gpu-marlin.yaml +2 -2

No files found.
--- a/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-multi-gpu-marlin.yaml
+++ b/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-multi-gpu-marlin.yaml
@@ -168,5 +168,5 @@
  replace:
    class: "default"
    kwargs:
-      generate_device: "cuda:0"
+      generate_device: "cuda:1"
-      prefill_device: "cuda:0"
+      prefill_device: "cuda:1"