One bidirectional connect-go stream per node, carrying registration, heartbeats and shard status up, and start, stop and drain down. The agent dials out: GPU nodes sit behind firewalls far more often than a control plane does, and an outbound connection needs no inbound rule on every node in the fleet. - registration carries the whole hardware inventory, so there is no separate discovery call and a reconnecting agent refreshes what the scheduler knows. The fabric labels travel with it; they cannot be inferred from the wire, so losing them in transit would silently disable multi-node placement. - agentsvc is both the stream handler and the reconciler's dispatcher, because it holds the open streams and is therefore the only thing that can deliver a command to a node. - the agent validates a profile before launching anything, since an engine that refuses a profile does so after minutes of loading, then supervises the process and reports every transition with the engine's output tail on failure. - reconnects forever with jittered backoff. A control plane restart must not require touching every GPU node, and a fleet must not reconnect in lockstep and knock it over again. Engines keep serving throughout, because the router talks to them directly. llmgw agent is real now, and llmgw server runs a control plane whenever any model declares a profile. The static endpoint list stays for router-only runs. Verified with real binaries as separate processes: the agent registers, a replica is placed, an engine launches through the vLLM adapter's actual argument construction, streaming traffic is served, and killing the agent moves the node through unreachable to lost with placement explaining why nothing can run. config.Model and catalog.Model were the same thing described twice, so the router now reads catalog entries directly and the validation rules live in one place. Still missing: mTLS. The stream is plaintext HTTP/2 and must stay on a trusted network until that lands. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
c1b9ea1bc2
commit
2373726efd
24 files changed
+3645
-87
No files matched your search
+27
-14
@@ -8,6 +8,10 @@
|
||||
|
||||
listen: ":8080" # client-facing OpenAI API
|
||||
admin_listen: ":9090" # metrics, health, pprof — do not expose this publicly
|
||||
# Where node agents connect. Separate from the client port so the fleet-facing
|
||||
# surface can be firewalled independently. Agents speak plaintext HTTP/2 today,
|
||||
# so this must stay on a trusted network until mTLS lands (plan §5.6).
|
||||
agent_listen: ":7443"
|
||||
|
||||
router:
|
||||
scrape_interval: 2s
|
||||
@@ -79,6 +83,19 @@ router:
|
||||
kv_ceiling: 0.9
|
||||
session_load_factor: 1.25
|
||||
|
||||
# How aggressively the control plane reconciles.
|
||||
control:
|
||||
interval: 5s
|
||||
base_backoff: 10s
|
||||
max_backoff: 10m
|
||||
# Node expiry is staged deliberately: a network blip must not tear down
|
||||
# replicas that are still serving, and rebuilding a multi-node replica costs
|
||||
# tens of minutes of model loading.
|
||||
unreachable_after: 15s
|
||||
lost_after: 60s
|
||||
port_range: [20000, 20999]
|
||||
mgmt_interface: eth0
|
||||
|
||||
models:
|
||||
- name: llama-3.3-70b
|
||||
aliases: [llama]
|
||||
@@ -89,17 +106,13 @@ models:
|
||||
aliases: [qwen]
|
||||
routing_profile: batch
|
||||
|
||||
endpoints:
|
||||
- id: gpu-a-01
|
||||
url: http://gpu-a-01:8000
|
||||
models: [llama-3.3-70b]
|
||||
pool: ib-a/h100-80g
|
||||
weight: 100 # from ctl bench; do not estimate it by hand
|
||||
priority: 100 # higher pools are tried first
|
||||
|
||||
- id: gpu-b-01
|
||||
url: http://gpu-b-01:8000
|
||||
models: [llama-3.3-70b, qwen2.5-32b]
|
||||
pool: ib-b/a100-80g
|
||||
weight: 45
|
||||
priority: 50
|
||||
# A static replica list, used only when no model declares a profile. That is the
|
||||
# router-only mode for testing against sim-engines; with the control plane
|
||||
# running, agents provide the replicas instead.
|
||||
#
|
||||
# endpoints:
|
||||
# - id: sim-1
|
||||
# url: http://127.0.0.1:8001
|
||||
# models: [llama-3.3-70b]
|
||||
# pool: local
|
||||
# weight: 1
|
||||
Reference in new issue
Block a user