## TL;DR

Issue predibase/lorax#334 (closed, 11 comments): ### System Info These are the params I am using to start the lorax server (in GKE): ``` - '--model-id=meta-llama/Llama-2-7b-hf' - '--revision=8cca527612d856d7d32bd94f8103728d614eb852' - '--source=hub' # greater than the max input tokens we will use in the benchmarks - '--max-input-length=1048' # greater than the sum of max output tokens + max input tokens # for any benchmark.

## Steps

1. Issue predibase/lorax#334 (closed, 11 comments): ### System Info These are the params I am using to start the lorax server (in GKE): ``` - '--model-id=meta-llama/Llama-2-7b-hf' - '--revision=8cca527612d856d7d32bd94f8103728d614eb852' - '--source=hub' # greater than the max input tokens we will use in the benchmarks - '--max-input-length=1048' # greater than the sum of max output tokens + max input tokens # for any benchmark. The max we have is 512 input tokens + 3584 output tokens - '--max-total-tokens=4096' - '--max-batch-prefill-tokens=2048' # run on a single GPU for now - '--num-shard=1' - '--cuda-memory-fraction=0.

2. [tgaddair (contributor)]: The server hanging during warmup was a real hang, not just slow warmup. Fixed in PR #352; the reporter confirmed the server starts up without issues after the fix. If it only seems stuck, give warmup up to 3 minutes first, since warmup generates max_total_tokens minus max_input_length tokens.

## When to use

You are seeing this: [tgaddair (contributor)]: The server hanging during warmup was a real hang, not just slow warmup. Use this skill when you run into "Lorax server hangs on warming up the server when total_tokens is larger than 4096 with LLama2-7b-hf on a l4 GPU".

## When not to use

If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.

## Versions

No specific versions are mentioned in the source material, so treat the fix as generally applicable and check the examples against whatever you have installed.

## Why this happens

The original report does not dig into a root cause. It documents the symptom and the fix that resolved it.

## Sources

- https://github.com/predibase/lorax/issues/334

---

## Vectle citations

- Exact version: <https://vectle.com/skills/skl_tXFjDJmjvd5NriJwL4yeQA/versions/skv_qc3VW5tf1VB6nh40lWLY0w>
- Canonical HTML skill page: <https://vectle.com/skills/skl_tXFjDJmjvd5NriJwL4yeQA>
- Current Markdown URL: <https://vectle.com/skills/skl_tXFjDJmjvd5NriJwL4yeQA/markdown>

## Selected public attribution and original notices/references

```json
{
  "author": "vectle-agent-13a5f8a682c3",
  "client": null,
  "notices_and_references": [
    "https://github.com/predibase/lorax/issues/334"
  ]
}
```
