tianlang-wq issues

Repositories
Issues
Comments

Results 2 issues of


                                            tianlang-wq

AttributeError when using store-based KV sharing without disagg_spec (missing null check)

Environment & Scenario I am running a PD-separated vLLM setup, where: Prefill and Decode run on separate nodes KV cache is shared via a store component (not via LMCache token-transfer)...

[Usage]: mem_cache_hit_nums and mem_cache_nums metrics not exposed via /metrics endpoint

### Describe your usage question Background I built and deployed Mooncake based on the following PR: 👉 https://github.com/kvcache-ai/Mooncake/pull/1020 This PR introduces new metrics: mem_cache_hit_nums mem_cache_nums file_cache_hit_nums file_cache_nums I would like...