Skip to content

GitLab

Unverified Commit 8128e08d authored by Ke Bao's avatar Ke Bao Committed by GitHub
Browse files

Turn off hybrid cache by default (#8839)

parent 5d62b56f
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 0 deletions
python/sglang/srt/server_args.py
View file @ 8128e08d
...@@ -461,6 +461,7 @@ class ServerArgs: ...@@ -461,6 +461,7 @@ class ServerArgs:
if model_arch in ["GptOssForCausalLM"]: if model_arch in ["GptOssForCausalLM"]:
self.attention_backend = "triton" self.attention_backend = "triton"
self.enable_triton_kernel_moe = True self.enable_triton_kernel_moe = True
self.disable_hybrid_swa_memory = True
# Set page size # Set page size
if self.page_size is None: if self.page_size is None:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment