Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

trtllm-build with --fast-build ignore transformer layers #2135

Closed
2 of 4 tasks
ZJLi2013 opened this issue Aug 21, 2024 · 4 comments
Closed
2 of 4 tasks

trtllm-build with --fast-build ignore transformer layers #2135

ZJLi2013 opened this issue Aug 21, 2024 · 4 comments
Assignees
Labels
not a bug Some known limitation, but not a bug. stale triaged Issue has been triaged by maintainers waiting for feedback

Comments

@ZJLi2013
Copy link

System Info

DGX H100

Who can help?

when build engine with :

  trtllm-build --fast-build --model_config $model_cfg 

and then benchmark with gptMangerBenchmark, it reports:

[08/21/2024-12:18:48] [TRT-LLM] [I] Total time of building Unnamed Network 0: 00:01:28
[08/21/2024-12:18:48] [TRT-LLM] [E] Failed to get weight: transformer.layers.0.attention.qkv.weight
[08/21/2024-12:18:48] [TRT-LLM] [E] Failed to get weight: transformer.layers.0.attention.dense.weight
[08/21/2024-12:18:48] [TRT-LLM] [E] Failed to get weight: transformer.layers.0.mlp.router.weight
[08/21/2024-12:18:48] [TRT-LLM] [E] Failed to get weight: transformer.layers.0.mlp.fc.weight
[08/21/2024-12:18:48] [TRT-LLM] [E] Failed to get weight: transformer.layers.0.mlp.proj.weight
# and further in runtime : 
[TensorRT-LLM][ERROR] Encountered an error in forwardAsync function: Input tensor 'transformer.layers.0.attention.qkv.weight' not found; expected shape: (8192, 1280) (/src/tensorrt_llm/cpp/tensorrt_llm/runtime/tllmRuntime.cpp:202)

is it expected behavior with fast-build ?

btw, wo --fast-build, the engine build and benchmark looks all right.

Thanks

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

  trtllm-build --fast-build --model_config $model_cfg 

Expected behavior

fast-build flag should also build workable engines,

actual behavior

with fast-build flag, transformer layers are ignored somehow

additional notes

no more

@ZJLi2013 ZJLi2013 added the bug Something isn't working label Aug 21, 2024
@VALLIS-NERIA
Copy link

Hi, please check:

Do you find a file named rank0_managed_weights.safetensors or so inside the engine dir?

Is there a field named manage_weights in config.json, plugin_config part?

@VALLIS-NERIA
Copy link

It seems that you are building from a model config without weights, not a checkpoint. In such cases TRT-LLM generates random weights, but is not supported by fast_build yet.

@lfr-0531 lfr-0531 added triaged Issue has been triaged by maintainers not a bug Some known limitation, but not a bug. waiting for feedback and removed bug Something isn't working labels Sep 7, 2024
Copy link

github-actions bot commented Oct 9, 2024

This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 15 days."

Copy link

github-actions bot commented Dec 4, 2024

This issue was closed because it has been 14 days without activity since it has been marked as stale.

@github-actions github-actions bot closed this as not planned Won't fix, can't repro, duplicate, stale Dec 4, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
not a bug Some known limitation, but not a bug. stale triaged Issue has been triaged by maintainers waiting for feedback
Projects
None yet
Development

No branches or pull requests

3 participants