TensorRT-LLMs/cpp/tensorrt_llm/kernels/trtllmGenKernels/blockScaleMoe
Zongfei Jing 7eee9a9d28
doc: Update doc for Deepseek min latency (#3717)
* Tidy code

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Update doc for min latency deepseek

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Throw exception for RouterKernel when not running on sm90+

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

---------

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
2025-04-22 23:07:59 +08:00
..
gemmCubins feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
trtllmGenSrc doc: Update doc for Deepseek min latency (#3717) 2025-04-22 23:07:59 +08:00
CMakeLists.txt feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
gemmCommon.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
gemmList.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
runner.cu feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
runner.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00