TensorRT-LLMs/cpp/tensorrt_llm/kernels/trtllmGenKernels/blockScaleMoe/trtllmGenSrc
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
..
DevKernel.cu feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
DevKernel.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
Dtype.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
DtypeDecl.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
Enums.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
KernelParams.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
KernelTraits.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
macros.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
RoutingKernel.cu doc: Update doc for Deepseek min latency (#3717) 2025-04-22 23:07:59 +08:00
RoutingKernel.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
SfLayout.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
SfLayoutDecl.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
TmaDescriptor.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
Utils.h feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00