[Router] Add bucket-aware policy domains and native cache indexing (#38108)

Signed-off-by: Vincent Gao <vincentbo@linux.alibaba.com>
Co-authored-by: inkcherry <mingzhi.liu@amd.com>
Co-authored-by: yangbodong22011 <13137470+yangbodong22011@users.noreply.github.com>
This commit is contained in:
Vincent Gao
2026-09-06 19:47:51 +08:00
committed by GitHub
co-authored by inkcherry yangbodong22011
parent a176ba2f7b
commit 5bebe7a033
76 changed files with 5842 additions and 3639 deletions
@@ -0,0 +1,35 @@
{
"ttft_slo_policy": "disabled",
"tps_slo_policy": "disabled",
"buckets": [
{
"id": "short",
"stage": "prefill",
"rank": 0,
"worker_ids": [
"http://127.0.0.1:31000",
"http://127.0.0.1:31001",
"http://127.0.0.1:31002",
"http://127.0.0.1:31003"
],
"min_extend_tokens": 0,
"max_extend_tokens": 2048,
"max_context_tokens": 32768,
"max_pending_prefill_tokens": 65536
},
{
"id": "long",
"stage": "prefill",
"rank": 1,
"worker_ids": [
"http://127.0.0.1:31004",
"http://127.0.0.1:31005",
"http://127.0.0.1:31006",
"http://127.0.0.1:31007"
],
"min_extend_tokens": 2049,
"max_context_tokens": 32768,
"max_pending_prefill_tokens": 65536
}
]
}