mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
Replace libtensorrt_llm_nvrtc_wrapper.so with its source code, which consists of two parts: 1. NVRTC glue code 2. XQA kernel code During TensorRT-LLM build, XQA kernel code is embedded as C++ arries via gen_cpp_header.py and passed to NVRTC for JIT compilation. Signed-off-by: Ming Wei <2345434+ming-wei@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| cubin | ||
| decoderXQAImplJIT | ||
| instantiation | ||
| CMakeLists.txt | ||
| copy_cu.py | ||
| decoderMaskedMultiheadAttentionLaunch.h | ||
| decoderMaskedMultiheadAttentionTemplate.h | ||
| decoderXQAConstants.h | ||
| decoderXQAImpl.cpp | ||
| decoderXQAImpl.h | ||
| decoderXQAImplCommon.cpp | ||
| decoderXQAImplCommon.h | ||
| decoderXQAImplPrecompiled.cpp | ||
| decoderXQAImplPrecompiled.h | ||
| decoderXQARunner.cpp | ||
| decoderXQARunner.h | ||
| mmha_notes.md | ||
| tensorMapUtils.cpp | ||
| tensorMapUtils.h | ||
| xqaParams.h | ||