Repository navigation
Drop the "newer than 2.15" marks from the TensorRT backend page - #24214
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24214
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 13e0a80 with merge base 0549e1e ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
|
@claude /pr-review |
|
Claude finished @shoumikhin's task in 11m 1s —— View job No blocking issues: the PR's 2.15 check doesn't cover part of each feature (low-confidence request to confirm), and two intro lines need a small wording fix. Full reviewPR Review: #24214SummaryThe PR drops the "newer than 2.15" marks from API Design
Code Quality
RecommendationApprove Nothing blocks. The 2.15 question needs only a one-line confirmation from the author, and the wording fix is minor. |
The TensorRT backend page marked two features as needing a Torch-TensorRT build newer than 2.15: keeping the engines in a separate .ptd data file, and optimization profiles. Both are in Torch-TensorRT 2.15, so the marks sent readers to a nightly build they do not need. The page now lists both as plain features, like the Torch-TensorRT guide does, and says that the engines go in the .pte by default.
a41cb18 to
13e0a80
Compare
|
Thanks, both points are addressed.
|
|
@pytorchbot cherry-pick --onto release/1.6 -c docs |
Cherry picking #24214The cherry pick PR is at #24221 Details for Dev Infra teamRaised by workflow job |
…rch#24214) The TensorRT backend page marked two features as needing a Torch-TensorRT build newer than 2.15: keeping the engines in a separate `.ptd` data file, and optimization profiles. Both are already in Torch-TensorRT 2.15, so the marks sent readers to a nightly build they do not need. This change drops the marks and lists both as plain features, the same way the Torch-TensorRT guide describes them. The links to the guide sections are unchanged. Two intro lines now say that the engines are stored in the `.pte` by default, since the `.ptd` option is no longer marked as newer. Checked on the Torch-TensorRT `release/2.15` branch: - `.ptd` engines: `external_engine_data` in `torch_tensorrt.save`, and the delegate reads the engine from the data file passed at load time (`data_path=` in Python, `Module(pte, ptd)` in C++). - Optimization profiles: `torch_tensorrt.Input(profiles=...)` at export, and `OptimizationProfileGuard` in the delegate header. - The linked export scripts and reference runner programs, including the multi-profile ones, are the same files on `release/2.15` as on `main`, so the links work for 2.15. Docs only; no code changes.
The TensorRT backend page marked two features as needing a Torch-TensorRT build newer than 2.15: keeping the engines in a separate
.ptddata file, and optimization profiles. Both are already in Torch-TensorRT 2.15, so the marks sent readers to a nightly build they do not need.This change drops the marks and lists both as plain features, the same way the Torch-TensorRT guide describes them. The links to the guide sections are unchanged. Two intro lines now say that the engines are stored in the
.pteby default, since the.ptdoption is no longer marked as newer.Checked on the Torch-TensorRT
release/2.15branch:.ptdengines:external_engine_dataintorch_tensorrt.save, and the delegate reads the engine from the data file passed at load time (data_path=in Python,Module(pte, ptd)in C++).torch_tensorrt.Input(profiles=...)at export, andOptimizationProfileGuardin the delegate header.release/2.15as onmain, so the links work for 2.15.Docs only; no code changes.