Refactors radix cache for extra key support (#10317)

Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-09-21 11:16:16 -07:00
parent fc3e542009
commit 12d6cf18f0
13 changed files with 821 additions and 574 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -99,6 +99,7 @@ suites = {
        TestFile("test_priority_scheduling.py", 100),
        TestFile("test_pytorch_sampling_backend.py", 66),
        TestFile("test_radix_attention.py", 105),
+        TestFile("test_radix_cache_unit.py", 5),
        TestFile("test_regex_constrained.py", 64),
        TestFile("test_reasoning_parser.py", 5),
        TestFile("test_retract_decode.py", 54),