From 91fc5bb5a98a1d7893d5782031baa362ff605ade Mon Sep 17 00:00:00 2001 From: Yineng Zhang Date: Tue, 14 Oct 2025 21:48:13 -0700 Subject: [PATCH] feat: add add_chunked_prefix_cache_attention_backend (#11636) --- python/sglang/srt/model_executor/model_runner.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/python/sglang/srt/model_executor/model_runner.py b/python/sglang/srt/model_executor/model_runner.py index b4eab1d5a..39ee02aaf 100644 --- a/python/sglang/srt/model_executor/model_runner.py +++ b/python/sglang/srt/model_executor/model_runner.py @@ -190,6 +190,14 @@ def add_mla_attention_backend(backend_name): logger.info(f"Added {backend_name} to MLA_ATTENTION_BACKENDS.") +def add_chunked_prefix_cache_attention_backend(backend_name): + if backend_name not in CHUNKED_PREFIX_CACHE_SUPPORTED_ATTENTION_BACKENDS: + CHUNKED_PREFIX_CACHE_SUPPORTED_ATTENTION_BACKENDS.append(backend_name) + logger.info( + f"Added {backend_name} to CHUNKED_PREFIX_CACHE_SUPPORTED_ATTENTION_BACKENDS." + ) + + _is_hip = is_hip() _is_npu = is_npu() _is_cpu_amx_available = cpu_has_amx_support()