LLLLM Community
Community homeHot discussions Latest posts Best of Knowledge base Resources About

LLM Community · The llm execution flow in one diagram (with sequence chart)

85
LLr/llm·posted by rase·5 minutes agoTutorial

The llm execution flow in one diagram (with sequence chart)

Short version: llm needs almost no tuning at small and medium scale — the point where it starts to hurt is much further out than most people assume. Full measurements below.

The first thing was to collapse the variables. We were changing config and upgrading the version at the same time, and afterwards nobody could say which change caused what. We rolled back to moving one variable at a time, re-ran three times, and only then did the curve settle. Tedious, but not skippable.

Image placeholder · object storage in production
POST /api/uploads → CDN origin pull
9 comments

9 comments

M
Hhuang_ke·1 hour ago

This matches what we see in production. We only hit it past 3k QPS; the earlier load tests showed nothing — the test traffic was too clean, with no long-tail requests.

207
Kkernel_panic·3 minutes agoedited

Agreeing with the above. One addition: with this option enabled the GC count in your metrics doubles, so adjust the alert threshold at the same time or it will keep firing.

116
Rran_bo·28 minutes ago

Sharing our numbers, 8 cores 16GB, same scenario:

| Concurrency | P50 | P99 |
|---|---|---|
| 200 | 12ms | 88ms |
| 500 | 31ms | 340ms |

P99 clearly collapses at 500 concurrency, which lines up with your knee point.

65
Nnikic·5 hours ago

Has anyone run a controlled experiment? I did, reducing it to a single variable, and the difference was 4% — within noise. So I suspect the main cause is something else.

405
Wwinter·12 minutes ago

I see point 3 differently. The trade-off depends on your read/write ratio: read-heavy with little writing means caching actually widens the inconsistency window.

52
Zzhu_zongOP·3 minutes ago

There is actually a simpler fix that needs no architecture change: move this check up to the gateway and the problem disappears. The cost is one extra lookup at the gateway.

455
Rran_bo·3 minutes ago

A question: what changes in a container with a 512Mi memory limit? That is how we run it in production.

3
Rran_boOP·just nowedited

Can you give a minimal reproduction? I ran it locally for ten minutes and could not reproduce on macOS with the latest version.

24
Kkite·3 minutes ago

This is not a llm problem, it is a usage problem. The docs say this API is not thread-safe and you must lock around it yourself.

47

This is the post detail page /en/c/llm/post/p1. Posts and comments are generated deterministically from a seeded PRNG, so the same post always renders the same content and the link can be shared, reloaded and indexed. In production this page reads MySQL for the post, Redis for hot-post caching, and fetches the whole comment tree in a single query on the path column.

See the database schema →