NVIDIA / NVIDIA/TensorRT-LLM

[Feature]: Check why we hit recompilation during RT

Open
#7,404 0 comments 0 reactions 1 assignee View on GitHub

Nobody has claimed this yet.

feature request Inference runtime
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

🚀 The feature, motivation and pitch

Investigate why recompilation during RT. It could be due to prefill graph does not use cuda graph due to memory limitation.

trtllm-bench --model meta-llama/Llama-3.1-8b throughput --dataset synthetic_128_128.txt --warmup 0 --backend _autodeploy --max_batch_size 256 --extra_llm_api_options /lustre/fs1/portfolios/coreai/users/egeva/autodeploy-dashboard/extra.yaml --tp=1

Read Lucas's links pasted to the weekly meeting doc: https://docs.google.com/document/d/1eg5XEnRC1LDsWmhJJprLlKqKs563C0jZn44NQJ9eggE/edit?disco=AAABp1DPRRE

Alternatives

No response

Additional context

No response

Before submitting a new issue...
  • Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.