Files
neuron-tai/.scratch/distributed-inference-performance/issues/07-prefill-backpressure.md
2026-07-10 01:30:07 +03:00

28 lines
1014 B
Markdown

Status: ready-for-agent
# 07 — Bounded prefill chunk backpressure
## What to build
Make large prefill transfer bounded across every Activation Seam. Chunk prompt
activations, limit in-flight chunks, and propagate downstream congestion so a
slow Shard node cannot cause the head or relay bridge to buffer the entire
context in memory. Keep decode-step traffic sequential and low-latency.
## Acceptance criteria
- [ ] Configurable prefill chunk size and in-flight limit exist with safe
defaults.
- [ ] Peak per-hop buffered bytes are bounded by the configured limits.
- [ ] A slow downstream stub applies backpressure and does not lose or reorder
chunks within a Route Session.
- [ ] Cancellation and route failure release queued chunks and local buffers.
- [ ] Tests cover small prompts, multi-chunk prompts, slow consumers, retry/fail
closeout, and legacy single-chunk peers.
## Blocked by
- 01 — Baseline and profiling harness.
- 04 — Activation Seam telemetry and bounded progress reporting.