vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-10 06:14:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #906 from Azure-Tang/main

Browse source 
[Fix] Fix rocm example yaml
This commit is contained in:
Azure 2025-03-16 10:27:59 +08:00 • committed by GitHub
commit 0e93a09d67
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/rocm/DeepSeek-V3-Chat.yaml
View file

@ -12,7 +12,7 @@
replace: replace:
class: ktransformers.operators.linear.KTransformersLinear # optimized Kernel on quantized data types class: ktransformers.operators.linear.KTransformersLinear # optimized Kernel on quantized data types
kwargs: kwargs:
generate_device: "cuda" generate_device: "cpu"
prefill_device: "cuda" prefill_device: "cuda"
generate_op: "KLinearCPUInfer" generate_op: "KLinearCPUInfer"
prefill_op: "KLinearTorch" prefill_op: "KLinearTorch"
@ -23,7 +23,7 @@
replace: replace:
class: ktransformers.operators.linear.KTransformersLinear # optimized Kernel on quantized data types class: ktransformers.operators.linear.KTransformersLinear # optimized Kernel on quantized data types
kwargs: kwargs:
generate_device: "cpu" generate_device: "cuda"
prefill_device: "cuda" prefill_device: "cuda"
generate_op: "KLinearQ8" generate_op: "KLinearQ8"
prefill_op: "KLinearTorch" prefill_op: "KLinearTorch"