vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-05 20:19:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

change inject yaml

Browse source
This commit is contained in:
qiyuxinlin 2025-04-29 08:09:39 +00:00
parent 2a224b256e
commit 48dfbc8f9f
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-fp8-linear-ggml-experts-serve.yaml
View file

@ -44,7 +44,7 @@
- match: - match:
name: "^model\\.layers\\..*\\.self_attn$" name: "^model\\.layers\\..*\\.self_attn$"
replace: replace:
class: ktransformers.operators.attention.flashinfer_attn # optimized MLA implementation class: ktransformers.operators.balance_serve_attention.flashinfer_attn # optimized MLA implementation
kwargs: kwargs:
generate_device: "cuda" generate_device: "cuda"
prefill_device: "cuda" prefill_device: "cuda"