[Bug]: Chunked prefill returning gibberish in some cases.

[fmmoret]

Your current environment

main branch Dockerfile.rocm default dependencies.

🐛 Describe the bug

--max-num-batched-tokens=131072 --enable-chunked-prefill -- perfect response. temp 0
--max-num-batched-tokens=16384 --enable-chunked-prefill -- gibberish response. temp 0

Using a prompt of 100001 seq length & generate 100 tokens.

With temp 0, the gibberish does NOT match itself across iterations
E.g.: Good response 1 = What? What?”\n\n“Why, the bridge was mined [...]
Bad response 1 = So far as Jiedgilliesgillies-illies-illies-er. A Jemel-er-illies-ied-: \xa0 [...]
Bad response 2 is entirely different from 1 = \xa0gillies in England-ied. A Jiedgeld-eren [...]

I haven't looked into the VLLM impl yet. It seems like maybe the tensors are not initialized correctly somewhere and are inheriting whatever values were already in memory at the time.

I have seen this kind of thing happen before when someone uses x = torch.empty(size) -- which initializes to whatever memory already had set for that segment -- when they meant to use / wanted zeros.

[github-actions]

This issue has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this issue should remain open. Thank you!

[github-actions]

This issue has been automatically closed due to inactivity. Please feel free to reopen if you feel it is still relevant. Thank you!