feat: Add TensorRT Multi-Device (multi-GPU) inference support (cherry-pick) - #122
Merged
Merged
Conversation
* Add TensorRT Multi-Device (multi-GPU) inference support Run a single TensorRT engine sharded across multiple GPUs via TensorRT Multi-Device (NCCL DistCollective + IExecutionContext::setCommunicator, GA in TensorRT 11). Enabled per-model with a KIND_MODEL instance group plus parameters enable_multi_device, multi_device_gpus, and multi_device_per_rank_engines; transparent to clients (same gRPC/HTTP API). Runtime: ncclCommInitAll, per-rank deserialize + setCommunicator (concurrent), adaptive P2P/host input replication, fan-out enqueueV3, rank-0 output. Supports offline-sharded engines and per-rank weight-shard (tensor-parallel) engines. docs/multi_device.md documents configuration + validation; docs/ includes engine builders used for testing. Validated on 2x and 8x B200 (NVLink). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Signed-off-by: Peter Kisfaludi <pkisfaludi@nvidia.com> * apply pre-commit hook --------- Signed-off-by: Peter Kisfaludi <pkisfaludi@nvidia.com> Co-authored-by: Peter Kisfaludi <pkisfaludi@nvidia.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This was referenced Jun 27, 2026
mc-nv
marked this pull request as ready for review
June 27, 2026 02:18
yinggeh
approved these changes
Jun 27, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does the PR do?
Cherry-picks
6cdd73dfromr26.06to advancemainpost-26.05 toward the 26.07dev_user container train (tracks upstream 26.06).Adds TensorRT multi-device (multi-GPU) inference support, with new docs (
docs/build_tp_engines.cpp,docs/create_onnx_multilayer.py,docs/multi_device.md).Related PRs:
Test plan:
Related Issues: