help="KV Router: Disable tracking of active blocks (blocks being used for ongoing generation). By default, active blocks are tracked for load balancing.",
help="KV Router: Disable tracking of active blocks (blocks being used for ongoing generation). By default, active blocks are tracked for load balancing.",
)
)
parser.add_argument(
"--no-assume-kv-reuse",
action="store_false",
dest="router_assume_kv_reuse",
default=True,
help="KV Router: When tracking active blocks, do not assume KV cache reuse (generate random hashes instead of computing actual block hashes). Useful when KV cache reuse is not expected. By default, KV cache reuse is assumed.",
@@ -31,6 +31,8 @@ The main KV-aware routing arguments:
...
@@ -31,6 +31,8 @@ The main KV-aware routing arguments:
-`--no-track-active-blocks`: Disables tracking of active blocks (blocks being used for ongoing generation/decode phases). By default, the router tracks active blocks for load balancing. Disable this when routing to workers that only perform prefill (no decode phase), as tracking decode load is not relevant. This reduces router overhead and simplifies state management.
-`--no-track-active-blocks`: Disables tracking of active blocks (blocks being used for ongoing generation/decode phases). By default, the router tracks active blocks for load balancing. Disable this when routing to workers that only perform prefill (no decode phase), as tracking decode load is not relevant. This reduces router overhead and simplifies state management.
-`--no-assume-kv-reuse`: When tracking active blocks, disables the assumption of KV cache reuse. By default (`router_assume_kv_reuse=true`), the router computes actual block hashes for sequence tracking to deduplicate blocks and optimize load balancing. When disabled via this flag, the router generates random hashes for sequence blocks, treating each request's blocks as unique. This is useful in disaggregated setups where prefill transfers blocks to decode workers that may already have those blocks cached, but the engine cannot coordinate transfers to avoid duplication. Without this flag, the router's load balancing heuristics would undercount decode blocks when duplicates exist.
-`--active-decode-blocks-threshold`: Initial threshold (0.0-1.0) for determining when a worker is considered busy based on KV cache block utilization. When a worker's KV cache active blocks exceed this percentage of total blocks, it will be marked as busy and excluded from routing. If not set, blocks-based busy detection is disabled. This feature works with all routing modes (`--router-mode kv|round-robin|random`) as long as backend engines emit `ForwardPassMetrics`. The threshold can be dynamically updated at runtime via the `/busy_threshold` HTTP endpoint (see [Dynamic Threshold Configuration](#dynamic-threshold-configuration)).
-`--active-decode-blocks-threshold`: Initial threshold (0.0-1.0) for determining when a worker is considered busy based on KV cache block utilization. When a worker's KV cache active blocks exceed this percentage of total blocks, it will be marked as busy and excluded from routing. If not set, blocks-based busy detection is disabled. This feature works with all routing modes (`--router-mode kv|round-robin|random`) as long as backend engines emit `ForwardPassMetrics`. The threshold can be dynamically updated at runtime via the `/busy_threshold` HTTP endpoint (see [Dynamic Threshold Configuration](#dynamic-threshold-configuration)).
-`--active-prefill-tokens-threshold`: Literal token count threshold for determining when a worker is considered busy based on prefill token utilization. When active prefill tokens exceed this threshold, the worker is marked as busy. If not set, tokens-based busy detection is disabled.
-`--active-prefill-tokens-threshold`: Literal token count threshold for determining when a worker is considered busy based on prefill token utilization. When active prefill tokens exceed this threshold, the worker is marked as busy. If not set, tokens-based busy detection is disabled.