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
3a94d80839
TensorRT-LLMs/cpp/include/tensorrt_llm
History
Xiwen Yu 1b846046dd fix kernel select code to recognize sm103/sm100f 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
2025-08-06 14:24:43 +08:00
..
batch_manager [TRTLLM-5508][feat] check input tokens + improve error handling (#5170) 2025-08-05 18:27:43 +01:00
common fix kernel select code to recognize sm103/sm100f 2025-08-06 14:24:43 +08:00
deep_gemm CUDA13 breaking changes: c++ compile successful 2025-08-06 14:24:40 +08:00
executor [nvbug/5374773] chore: Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache (#5974) 2025-07-25 18:10:40 -04:00
kernels fix: compatibility with CUDA < 12.9 on __CUDA_ARCH_SPECIFIC__ macro (#5917) 2025-07-28 16:02:26 +08:00
layers v1.2 (#3082) 2025-03-26 23:31:29 +08:00
plugins/api Update TensorRT-LLM (#2532) 2024-12-04 21:16:56 +08:00
runtime [TRTLLM-4406][feat] LLM sleep & wakeup Part 1: virtual device memory (#5034) 2025-08-04 13:51:01 +08:00