kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
f5281fffaa
TensorRT-LLMs/cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/decoderXQAImplJIT
History
Yao Yao 3545d59635
Support speculative decoding with Hopper XQA (#3269) 
Signed-off-by: Yao Yao <lowsfer@users.noreply.github.com>
2025-04-07 17:14:34 +08:00
..
nvrtcWrapper Support speculative decoding with Hopper XQA (#3269) 2025-04-07 17:14:34 +08:00
compileEngine.cpp Support speculative decoding with Hopper XQA (#3269) 2025-04-07 17:14:34 +08:00
compileEngine.h Update TensorRT-LLM (#1554) 2024-05-07 23:34:28 +08:00
cubinObj.cpp Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
cubinObj.h Update TensorRT-LLM (#2755) 2025-02-11 03:01:00 +00:00
cubinObjRegistry.h fix: segfault in cudaDriverWrapper (#3017) 2025-04-02 08:55:19 +02:00
decoderXQAImplJIT.cpp Support speculative decoding with Hopper XQA (#3269) 2025-04-07 17:14:34 +08:00
decoderXQAImplJIT.h Support speculative decoding with Hopper XQA (#3269) 2025-04-07 17:14:34 +08:00
kernelUtils.cpp Support speculative decoding with Hopper XQA (#3269) 2025-04-07 17:14:34 +08:00
kernelUtils.h Update TensorRT-LLM (#2755) 2025-02-11 03:01:00 +00:00
serializationUtils.h Update TensorRT-LLM (#1554) 2024-05-07 23:34:28 +08:00