TensorRT-LLMs/cpp/tensorrt_llm/plugins
Daniel Stokes f7c597ec40
[None][perf] Make finalize fusion part of the tactic selection logic (#6915)
Signed-off-by: djns99 <40156487+djns99@users.noreply.github.com>
2025-08-21 14:08:03 -07:00
..
api
bertAttentionPlugin
common
cpSplitPlugin
cudaStreamPlugin
cumsumLastDimPlugin
doraPlugin
eaglePlugin
fp4GemmPlugin
fp8RowwiseGemmPlugin
fusedLayernormPlugin
gemmAllReducePlugin
gemmPlugin
gemmSwigluPlugin
gptAttentionCommon
gptAttentionPlugin
identityPlugin
layernormQuantizationPlugin
lookupPlugin
loraPlugin
lowLatencyGemmPlugin
lowLatencyGemmSwigluPlugin
lruPlugin
mambaConv1dPlugin
mixtureOfExperts
ncclPlugin
qserveGemmPlugin
quantizePerTokenPlugin
quantizeTensorPlugin
quantizeToFP4Plugin
rmsnormQuantizationPlugin
selectiveScanPlugin
smoothQuantGemmPlugin
topkLastDimPlugin
weightOnlyGroupwiseQuantMatmulPlugin
weightOnlyQuantMatmulPlugin
CMakeLists.txt
exports.def
exports.map