TL

GPU Inference Decision Lab

EKS/vLLM measurements support admission, long-context boundaries, scheduler defaults, useful-work cost, and FP8 KV rejection.

Serving infrastructure7 experiments · 9 decisions
Platform
AWS EKS + vLLM
Scale signal
Prometheus -> HPA
Baseline
0 serving GPUs

Decisions

Architecture Decisions

Admission + readiness

Supported

Use bounded admission when requests can arrive before model readiness.

100% queued delivery; direct clients dropped 237-787 iterations.

In progress

Optimize readiness before treating node launch as the cold-start bottleneck.

NodeClaim and GPU node arrival were fast; image, container, and model readiness drove the 425-439s wait. Next: Capture first-successful-completion timing across the selected cold-start reports.

Long-context scheduling

Supported

Set a concurrency or admission boundary for 8192/300 traffic.

1.20 req/s still delivers 100%, but repeats 36.8s p95 queue delay.

Rejected

Do not use seq caps or larger batched-token caps as the first 1.20 req/s fix.

seqs-16 hit 76.24s p95; seqs-24 hit 61.36s; batched-16384 hit 55.58s.

Supported

Keep vLLM dynamic defaults for current 512/128 steady and burst traffic.

Dynamic default kept the best delivery and token throughput.

Cost + autoscaling

Supported

Use batching for small-request economics, but gate burst SLO claims.

$0.019752/1K steady optimized; burst optimized p95 still 10.91s.

In progress

Keep active-pressure HPA testing, but do not treat target 8 as optimal.

Targets 2/4/6/8 were all underutilized. Next: Run a higher-pressure HPA sweep that reaches clear GPU utilization separation.

Quantization + hardware

Rejected

Do not select FP8 KV for this current long-context path.

47.58-69.12% delivery versus 100% baseline.

In progress

Hold the FP4 architecture decision until B200 results exist.

EC2 UnfulfillableCapacity; no quantized artifact produced. Next: Rerun once B200 capacity can produce a comparable quantized artifact.

Evidence visual

Where the latency lives

Queue attribution

vLLM timing separates queue, TTFT, and decode; admission removes queue inflation while decode stays roughly unchanged.

1.10 req/s

stable repeat; p95 decode 29.32s

p95 queue0.285s
p95 TTFT0.733s

1.15 req/s

queueing repeat; p95 decode 29.41s

p95 queue14.02s
p95 TTFT18.12s

1.20 req/s

queue-dominated; p95 decode 29.43s

p95 queue36.93s
p95 TTFT37.61s

1.25 admission

59 unserved; p95 decode 29.39s

p95 queue0.285s
p95 TTFT0.718s

Server timing from May 17-18 direct and admission-capped long-context reports

Evidence archive

Experiments

The measured runs behind the decisions — each detail page keeps the run shape, commands, and result evidence.