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

How to generate words in your example of cpp executor? #2662

Open
yjjuan opened this issue Jan 6, 2025 · 0 comments
Open

How to generate words in your example of cpp executor? #2662

yjjuan opened this issue Jan 6, 2025 · 0 comments

Comments

@yjjuan
Copy link

yjjuan commented Jan 6, 2025

  • I have succeeded in running your basic example of cpp executor. Currently, it only generated token_ids. Could you provide more instructions on how to turn these token ids into human-readable words?
root@ad3499615250:/workspace/TensorRT-LLM_0_16_0/examples/cpp/executor/build# ./executorExampleBasic ../../../llama/tinyllama-engine/ 
[TensorRT-LLM][INFO] Engine version 0.16.0 found in the config file, assuming engine(s) built by new builder API.
[TensorRT-LLM][INFO] Initializing MPI with thread mode 3
[TensorRT-LLM][INFO] Initialized MPI
[TensorRT-LLM][INFO] Refreshed the MPI local session
...
[TensorRT-LLM][INFO] [MemUsageChange] Allocated 1.52 GiB for max tokens in paged KV cache (72256).
[TensorRT-LLM][INFO] Output tokens: (1, 2, 3, 4, 29889, 13, 1576, 29871, 29906)
[TensorRT-LLM][INFO] Refreshed the MPI local session
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant