TensorRT-LLMs/cpp/tensorrt_llm/plugins
Ludwig Schneider 41ce14ab04
[None][feat] Enable NCCL_SYMMETRIC as default fallback for AllReduce (#9314)
Signed-off-by: Ludwig Schneider <lschneider@nvidia.com>
2025-12-07 09:43:26 -08:00
..
api Update TensorRT-LLM (#2783) 2025-02-13 18:40:22 +08:00
bertAttentionPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
common refactoring: port customized kernels with public cutlass version (#5027) 2025-06-13 16:19:31 +08:00
cpSplitPlugin Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
cudaStreamPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
cumsumLastDimPlugin Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
doraPlugin Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
eaglePlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
fp4GemmPlugin refactoring: port customized kernels with public cutlass version (#5027) 2025-06-13 16:19:31 +08:00
fp8RowwiseGemmPlugin Mxfp8xmxfp4 quant mode(#4978) 2025-06-10 22:01:37 +08:00
fusedLayernormPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
gemmAllReducePlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
gemmPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
gemmSwigluPlugin Mxfp8xmxfp4 quant mode(#4978) 2025-06-10 22:01:37 +08:00
gptAttentionCommon [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
gptAttentionPlugin [TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086) 2025-10-14 08:23:16 -07:00
identityPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
layernormQuantizationPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
lookupPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
loraPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
lowLatencyGemmPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
lowLatencyGemmSwigluPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
lruPlugin Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
mambaConv1dPlugin Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
mixtureOfExperts [None][fix] Fix the performance issue of FP8 blockwise grouped GEMM when using attention DP (#8501) 2025-10-27 10:18:19 +08:00
ncclPlugin [None][feat] Enable NCCL_SYMMETRIC as default fallback for AllReduce (#9314) 2025-12-07 09:43:26 -08:00
qserveGemmPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
quantizePerTokenPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
quantizeTensorPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
quantizeToFP4Plugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
rmsnormQuantizationPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
selectiveScanPlugin Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
smoothQuantGemmPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
topkLastDimPlugin Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
weightOnlyGroupwiseQuantMatmulPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
weightOnlyQuantMatmulPlugin [None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851) 2025-09-25 21:02:35 +08:00
CMakeLists.txt feat: reduce unnecessary kernel generation (#5476) 2025-07-04 14:37:49 +08:00
exports.def Update 2023-10-10 23:22:17 -07:00
exports.map Update TensorRT-LLM (#1530) 2024-04-30 17:19:10 +08:00