NVIDIA / NVIDIA/TensorRT-LLM

TensorRT-LLM- No free block found.

Open
#3,426 1 comment 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

System Info

We encountered a runtime crash while performing inference with TensorRT-LLM. The error message indicates a failure in the memory allocation system, specifically that no free memory block was available and the eviction policy failed to recover space.
[TensorRT-LLM][ERROR] Encountered an error in forwardAsync function: [TensorRT-LLM][ERROR] Assertion failed: No free block found. This shouldn't happen! (/src/tensorrt_llm/cpp/tensorrt_llm/batch_manager/evictionPolicy.cpp:89)

Who can help?

No response

Information
  • The official example scripts
  • My own modified scripts
Tasks
  • An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
  • My own task or dataset (give details below)
Reproduction

cannot be 100% reproduced

Expected behavior

efficient memory block management

actual behavior

No

additional notes

no free memory block

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.

Research direction

Start by inspecting tensorrt_llm/cpp/tensorrt_llm/batch_manager/evictionPolicy.cpp at line 89 and trace the forwardAsync path that reports the assertion. The issue has no reliable reproduction, so first determine which allocation and eviction conditions lead to the failure. Done means identifying and correcting the no-free-block condition, with a reproducible test or confirmed inference scenario.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
backend, machine-learning, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.