[Bug]: kv_cache_utils warns that prefix-cache reuse is disabled even when disable_eagle_block_drop keeps it working
![[Bug]: kv_cache_utils warns that prefix-cache reuse is disabled even when disable_eagle_block_drop keeps it working](https://www.chat-gpts.plus/wp-content/uploads/2026/11/55518-05700b36-768x403.jpg)
这个报错通常出现在 vLLM 启用 EAGLE 投机解码,同时模型含 Mamba KV group,并通过 --speculative-config 设置 "disable_eagle_block_drop": true 的场景。实际应以 use_eagle_block_drop() 是否启用作为判
![[Bug]: bench serve drops custom headers when stopping the profiler](https://www.chat-gpts.plus/wp-content/uploads/2026/11/55746-ba300666-768x403.jpg)





![[Bug]: GLM-5.2 MTP accepts 0% of drafts on MI355X (gfx950); disabling expert parallelism hits hipErrorIllegalAddress](https://www.chat-gpts.plus/wp-content/uploads/2026/11/52833-24d1036b-768x403.jpg)

