Update TensorRT-LLM (NVIDIA#1793)

Co-authored-by: DreamGenX <x@dreamgen.com>
Co-authored-by: Ace-RR <78812427+Ace-RR@users.noreply.github.com>
Co-authored-by: bprus <39293131+bprus@users.noreply.github.com>
Co-authored-by: janpetrov <janpetrov@icloud.com>

Author: 5 people

benchmarks/cpp/README.md

@@ -232,7 +232,7 @@ ${HOME}/.local/bin/trtllm-build \
     --output_dir ${LORA_ENGINE} \
     --max_batch_size ${MAX_BATCH} \
     --max_input_len $MAX_LEN \
-    --max_output_len $MAX_LEN \
+    --max_seq_len $((2*${MAX_LEN})) \
     --gemm_plugin float16 \
     --lora_plugin float16 \
     --use_paged_context_fmha enable \

benchmarks/cpp/bertBenchmark.cpp

@@ -17,6 +17,7 @@
 #include "tensorrt_llm/common/memoryUtils.h"
 #include "tensorrt_llm/plugins/api/tllmPlugin.h"
 #include "tensorrt_llm/runtime/iTensor.h"
+#include "tensorrt_llm/runtime/rawEngine.h"
 #include "tensorrt_llm/runtime/tllmLogger.h"
 #include "tensorrt_llm/runtime/tllmRuntime.h"
 #include "tensorrt_llm/runtime/worldConfig.h"
@@ -78,11 +79,10 @@ void benchmarkBert(std::string const& modelName, std::filesystem::path const& da
 {
     auto const worldConfig = WorldConfig::mpi();
     auto const enginePath = dataPath / engineFilename(dataPath, worldConfig, modelName);
-    auto engineBlob = loadEngine(enginePath.string());
 
     for (float gpuWeightsPercent : gpuWeightsPercents)
     {
-        auto rt = std::make_shared<TllmRuntime>(engineBlob.data(), engineBlob.size(), gpuWeightsPercent, *logger);
+        auto rt = std::make_shared<TllmRuntime>(RawEngine(enginePath), logger.get(), gpuWeightsPercent);
         rt->addContext(0);
         for (auto inLen : inLens)
         {