关联 Issue #5543 [Bug]: prefix-caching: inconsistent completions #33123 [Bug][ROCm]: Prefix caching produces different output on first request (cache miss) vs subsequent requests (cache hit) #42699 [Bug]: Prefix-read and no-prefix-read paths can yield different greedy answers for the same prompt #54490 [Bug]: enabling prefix caching changes deterministic repeated output
参与讨论