github-featured/nvidia--tensorrt
2
0
Fork 0
Code Issues Pull Requests Deployments Models Agent Notes Packages Projects Releases Wiki Activity
603 Commits 42 Branches 72 Tags
main
Commit Graph

37 Commits

Author SHA1 Message Date
Kevin Chen 771d8efdf7 TensorRT 11.0 OSS Release (#4799) 
Signed-off-by: Kevin Chen <kevinch@nvidia.com>
 2026-06-02 15:04:59 -07:00
Kevin Chen 52399f555c TensorRT 10.16 OSS Release (#4729) 
Signed-off-by: Kevin Chen <kevinch@nvidia.com>
 2026-03-25 16:20:12 -07:00
asfiyab-nvidia 3b4ddc1d45 TensorRT Release 10.14 (#4633) 
Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>
 2025-11-07 16:11:33 -08:00
Kevin Chen b8db91e15b TensorRT 10.13 OSS Release (#4531) 
Signed-off-by: Kevin Chen <kevinch@nvidia.com>
 2025-07-24 14:58:47 -07:00
Leo Dong 8c6d69ddec TensorRT 10.9 OSS Release. (#4381) 
Signed-off-by: Leo Dong <leod@nvidia.com>
 2025-03-11 14:54:52 -07:00
Yuan Yao a180e08111 10.8 release changes 
Signed-off-by: Yuan Yao <yuanyao@nvidia.com>
 2025-01-31 10:17:00 -08:00
Kevin Chen 17003e43da TensorRT 10.7-GA OSS Release (#4269) 
Signed-off-by: Kevin Chen <kevinch@nvidia.com>
 2024-12-05 13:12:22 -08:00
Kevin Chen c468d67760 TensorRT 10.6-GA OSS Release (#4238) 
Signed-off-by: Kevin Chen <kevinch@nvidia.com>
 2024-11-05 13:52:52 -08:00
poweiw c664ce22b0 Update for 10.4-GA 
Signed-off-by: poweiw <poweiw@nvidia.com>
 2024-09-11 17:26:50 -07:00
Yuan Yao 2332a7191d 10.2 GA release update (#3998) 
* 10.2 GA updates

Signed-off-by: Yuan Yao (yuanyao) <yuanyao@nvidia.com>

* update changelog

Signed-off-by: Yuan Yao (yuanyao) <yuanyao@nvidia.com>

* revert plugin README format changes

Signed-off-by: Yuan Yao (yuanyao) <yuanyao@nvidia.com>

---------

Signed-off-by: Yuan Yao (yuanyao) <yuanyao@nvidia.com>
 2024-07-11 10:18:43 -07:00
Asfiya Baig d3107c885a TensorRT 10.0 GA Release 
Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>
 2024-04-30 10:00:50 -07:00
Asfiya Baig 147005ffe1 TensorRT 10.0 Release 
Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>
 2024-04-02 17:06:37 -07:00
Ilya Sherstyuk c89bc8368a Update TensorRT to 8.6.1 
Signed-off-by: Ilya Sherstyuk <isherstyuk@nvidia.com>
 2023-05-04 20:53:55 -07:00
Ilya Sherstyuk eb2f188c55 Run clang-format on all .cpp and .h plugin code 
Signed-off-by: Shuyue Lan <shuyuel@nvidia.com>
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2023-03-16 20:53:29 -07:00
Vincent Huang 8508a9caf8 Various minor updates for plugins - part 5 
use kINT32 type for mask output in embLayerNormVarSeqlen plugin
Corrects PillarScatter supported formats
Fix bug when reading yaml file

Signed-off-by: Shuyue Lan <shuyuel@nvidia.com>
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2023-03-16 20:53:29 -07:00
Jin Li (Engrg-Hardware 1) e8d5e1671f Various minor fixes for plugins 
Limit output_dims == W[1] for plugin test
update embLayernorm plugin doc
Remove else after return as they are not required.
Fix FlattenConcat plugin readme

Signed-off-by: Shuyue Lan <shuyuel@nvidia.com>
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2023-03-15 17:38:49 -07:00
Samurdhi Karunaratne 8de77781b5 use kINT32 for BERT MHA plugin mask 
Signed-off-by: Shuyue Lan <shuyuel@nvidia.com>
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2023-03-15 17:38:49 -07:00
asfiyab-nvidia b0c259a749 TensorRT OSS - 8.5.3.1 Release (#2630) 
Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>
 2023-02-03 12:26:51 -08:00
Simeng Liu 1d6bf36034 TensorRT 8.5.1 OSS Release 
Update tools including onnx-graphsurgeon(v0.3.25), Polygraphy(v0.43.1), tensorflow-quantization(v0.2.0)
Update onnx-tensorrt(8.5GA)
Mass merge sample, plugin, demo, python changes for TRT-8.5 GA release
Update demoBERT benchmark data for TensorRT 8.5.1

Signed-off-by: Simeng Liu <simengl@nvidia.com>

Signed-off-by: Simeng Liu <simengl@nvidia.com>
 2022-11-02 16:43:34 -07:00
Po-Han Huang aca7586bc4 2003 - Fix OOB accesses in demoBERT embedLayerNorm plugins 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2022-06-14 14:23:17 -07:00
Rajeev Rao 60d62e66d2 Replace behavior of PLUGIN_ASSERT for attribute tests 
This graceful failure is needed to enable tests under `trt_mod_test`.

`PLUGIN_ASSERT` is used in many places inside plugin methods, most of
which are `noexcept` and do not contain try-catch blocks. So changing
`PLUGIN_ASSERT` would require a major refactor which is beyond
rel-8.4.  Instead, this MR introduces `PLUGIN_VALIDATE` as a temporary
replacement for `PLUGIN_ASSERT` in places where it is required to enable
valid/invalid attribute tests (mostly `createPlugin` and plugin constructors).
i.e. `PLUGIN_VALIDATE` implements the expected behavior of `PLUGIN_ASSERT`
(throws) while `PLUGIN_ASSERT` still aborts.

Signed-off-by: samurdhi karunaratne <skarunaratne@nvidia.com>
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2022-06-14 14:23:17 -07:00
Rajeev Rao 09dce45f91 TensorRT plugins updates for rel-8.4 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2022-06-14 14:23:17 -07:00
Rajeev Rao 052281f0ab Update copyright headers with SPDX identifiers 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2022-04-13 18:16:54 -07:00
Reese Wang 14594a1dc0 Extend Megatron plugins (embln, skipln) ld support 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2022-02-04 08:23:59 -08:00
Rajeev Rao 2d517d270e TensorRT OSS v8.2 Early Access Release 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2021-10-05 11:30:06 -07:00
Rajeev Rao aff45dd565 TensorRT OSS 8.0 release 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2021-07-02 16:35:44 -07:00
Rajeev Rao 64fa61b415 Add varlen MHA fp16 slen=384 kernels for sm_86 
1. add varlen mha fp16 slen=384 kernel for sm_86
2. referesh all sm_86 kernels now use NVCC -gencode=arch=compute_86,code=\"sm_86\"
3. use unfused kernel for fixed len s=384 fp16

Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2021-04-12 14:56:06 -07:00
Vincent Huang 2e875dbb28 fix doc for bert plugins 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2021-04-12 14:56:06 -07:00
Rajeev Rao cc5dede848 clang-format plugins and samples 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2021-04-12 14:56:06 -07:00
Rajeev Rao 183f891191 Update onnx-tensorrt and copyright headers (2021) 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2021-01-14 01:16:45 -08:00
Rajeev Rao 492878b2df TensorRT OSS release v7.2.1 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2020-10-20 16:48:23 -07:00
Rajeev Rao 805810b112 TensorRT 7.1 Open Source Release 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2020-07-01 16:31:50 -07:00
Rajeev Rao eff9163466 BERT kernel improvements 
- Softmax and batched GEMM tuning
- Increase tuning runs qkv
- Softmax and batched GEMM tuning

Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2020-06-17 13:48:22 -07:00
Rajeev Rao 572d54f917 TensorRT Open Source Release v7.0 
Release Notes:
https://docs.nvidia.com/deeplearning/sdk/tensorrt-release-notes/tensorrt-7.html

Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2019-12-18 15:18:32 -08:00
Kevin Chen 98ab844a6c Adding support for building BERT plugins with GPU_ARCHS specified (#255) 2019-12-05 15:48:18 -08:00
Kevin Chen fb305dea28 Fixing compilation issue in embLayerNormPlugin (#248) 2019-12-03 10:45:49 -08:00
Pranav Marathe 77af534c21 Moves BERT plugins into main plugin library, removes demo (will be relocated to DeepLearningExamples shortly) 
Signed-off-by: pranavm <pranavm@nvidia.com>
 2019-11-13 13:48:15 -08:00