Skip to content

build: DIS-148 use the tensorrt_llm public wheel from pypi by default in container build #1525

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.

Sign up for GitHub

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

Merged
richardhuo-nv merged 5 commits into from
Jun 16, 2025
Merged

build: DIS-148 use the tensorrt_llm public wheel from pypi by default in container build #1525

Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
0e26be6
default to build the release version of trtllm
richardhuo-nv Jun 12, 2025
00724cc
update readme
richardhuo-nv Jun 13, 2025
7885df6
fix show_help
richardhuo-nv Jun 13, 2025
9470c01
fix note
richardhuo-nv Jun 13, 2025
4c6081b
downgrade to 0.21.0rc0
richardhuo-nv Jun 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
fix note
  • Loading branch information
@richardhuo-nv
richardhuo-nv committed Jun 13, 2025
commit 9470c01fde6ea32b764a8b008ea7d19b15be3a0f
2 changes: 1 addition & 1 deletion examples/tensorrt_llm/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,7 +143,7 @@ dynamo serve graphs.agg:Frontend -f configs/deepseek_r1/mtp/mtp_agg.yaml
Notes:
- MTP is only available within the container built with the experimental TensorRT-LLM commit. Please add --use-default-experimental-tensorrtllm-commit to the arguments of the build.sh script.

ex: `./container/build.sh --framework tensorrtllm --use-default-experimental-tensorrtllm-commit`
Example: `./container/build.sh --framework tensorrtllm --use-default-experimental-tensorrtllm-commit`

- There is a noticeable latency for the first two inference requests. Please send warm-up requests before starting the benchmark.
- MTP performance may vary depending on the acceptance rate of predicted tokens, which is dependent on the dataset or queries used while benchmarking. Additionally, `ignore_eos` should generally be omitted or set to `false` when using MTP to avoid speculating garbage outputs and getting unrealistic acceptance rates.
Expand Down
Loading