mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
db7446fda7
* feat: add deepgemm_swapab feat: add fp8_gemm_kernel_swapab Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com> feat: set threshold for deepgemm and deepgemmswapab Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com> * docs: update README.md Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com> * fix: std::runtime_error needs #include <stdexcept> Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com> * chores: remove the redundant code Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com> * feat: support for dense deep_gemm swapab Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com> * chores: remove redundant code Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com> --------- Signed-off-by: Ruoqian Guo <ruoqiang@nvidia.com> Co-authored-by: Tao Li @ NVIDIA <tali@nvidia.com> |
||
|---|---|---|
| .. | ||
| bert | ||
| commandr | ||
| deepseek_v3 | ||
| enc_dec | ||
| exaone | ||
| gemma | ||
| glm-4-9b | ||
| gpt | ||
| granite | ||
| internlm2 | ||
| llama | ||
| mamba | ||
| mixtral | ||
| mllama | ||
| multimodal | ||
| nemotron | ||
| nemotron_nas | ||
| phi | ||
| qwen | ||
| qwen2audio | ||
| qwenvl | ||
| recurrentgemma | ||
| vit | ||
| whisper | ||