TensorRT · Beginners · This tensorrt-newbie bug hid for three years before anyone reported it

One counter-example: below tensorrt-newbie 7.4 the semantics of that code are different, so do not copy it verbatim. We got burned in staging and rolled back once.

Thanks for sharing real numbers — far more useful than the articles that only cover concepts.

I just read the tensorrt-newbie source — the author actually explains the reasoning in a comment, roughly "so that it degrades into predictable behaviour in extreme cases".

Saved. I am reworking this area this week — this saves a lot of wrong turns.

Saved. I am reworking this area this week — this saves a lot of wrong turns.

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.

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

Thanks for sharing real numbers — far more useful than the articles that only cover concepts.

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

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

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.

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.

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

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

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.

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.

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

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

Worth learning from this debugging approach. We went straight at the logs and took a much longer route.

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

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.

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.

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.

Thanks for sharing real numbers — far more useful than the articles that only cover concepts.

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

One counter-example: below tensorrt-newbie 7.4 the semantics of that code are different, so do not copy it verbatim. We got burned in staging and rolled back once.

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.

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.

I just read the tensorrt-newbie source — the author actually explains the reasoning in a comment, roughly "so that it degrades into predictable behaviour in extreme cases".

I just read the tensorrt-newbie source — the author actually explains the reasoning in a comment, roughly "so that it degrades into predictable behaviour in extreme cases".

One counter-example: below tensorrt-newbie 7.4 the semantics of that code are different, so do not copy it verbatim. We got burned in staging and rolled back once.

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.

I just read the tensorrt-newbie source — the author actually explains the reasoning in a comment, roughly "so that it degrades into predictable behaviour in extreme cases".

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.

Thanks for sharing real numbers — far more useful than the articles that only cover concepts.

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

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.

Thanks for sharing real numbers — far more useful than the articles that only cover concepts.

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.

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.

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

I just read the tensorrt-newbie source — the author actually explains the reasoning in a comment, roughly "so that it degrades into predictable behaviour in extreme cases".

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.

Saved. I am reworking this area this week — this saves a lot of wrong turns.

Worth learning from this debugging approach. We went straight at the logs and took a much longer route.

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.

One counter-example: below tensorrt-newbie 7.4 the semantics of that code are different, so do not copy it verbatim. We got burned in staging and rolled back once.

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.

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.