[Deps] Enable lmcache 0.5.4 with the kvaware router stack

[tyler2cr]

The "enable the new version of lmcache with vllm-stack" change, as a standalone diff (3 files, +18/−5) — independent of the chat-tokenization PR (vllm-project#1045); mergeable in either order.

What it changes

pin	before	after
[lmcache] extra: lmcache	0.3.11	0.5.4 (current stable)
[lmcache] / [test] extras: vllm	0.13.0	0.22.0
docker/Dockerfile.kvaware base	lmcache/vllm-openai:2025-05-27-v1	lmcache/vllm-openai:v0.5.4
tutorial-17 engine image	v0.3.9post2	v0.5.4

Each pin site now carries a comment documenting why the versions must move in lockstep — the two silent failure modes we hit on hardware:

1. lmcache's controller↔worker ZMQ messages are not a stable protocol across versions: a 0.3.x controller rejects a 0.4+/0.5+ worker's RegisterMsg as "unknown message type," and the worker never registers — every KV lookup misses, routing degrades to session/QPS with no error.
2. kv-aware chunk hashes are rooted in vLLM's NONE_HASH — a router whose vllm differs from the engines' derives a different hash chain, and again every lookup silently misses.

Verification

• Router's full lmcache API surface probed against 0.5.4: LMCacheControllerManager constructor (unchanged signature + two new optional params), handle_orchestration_message, start_all, LookupMsg, QueryInstMsg — all construct and behave.
• Full router test suite: 220/220 at this branch.
• The 0.4.5 pairing of the same wiring was validated end-to-end on hardware (2×H200 + 1×H100 runs — see [Router][Bugfix] KV-aware routing: tokenize chat-completions bodies through the chat template vllm-project/production-stack#1045's validation section).

One heads-up for 0.5.4 adopters

lmcache 0.5.4 still defaults lmcache_worker_heartbeat_time: None — workers never send heartbeats by default, while the controller reaps silent workers after ~30s, emptying the KV index shortly after startup ("misses that shouldn't be occurring"). The helm chart already maps lmcacheConfig.workerHeartbeatTime → LMCACHE_LMCACHE_WORKER_HEARTBEAT_TIME and tutorial-17's values set it to "30", so chart-driven deployments are safe — but any hand-rolled engine config must set it explicitly.

🤖 Generated with Claude Code

[tyler2cr]

Submitted upstream as vllm-project#1060 — that's now the canonical review venue; closing this staging PR. The branch stays available for interim image builds.