hlu1 d2f312b8e4 Fix fp8 kvcache (#3877) ... Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com@users.noreply.github.com> Co-authored-by: Hao Lu <14827759+hlu1@users.noreply.github.com@users.noreply.github.com>		2025-04-29 10:31:10 +08:00
..
utils	feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387)	2025-04-21 10:01:33 +08:00
__init__.py	Update TensorRT-LLM (#2792)	2025-02-18 21:27:39 +08:00
functional.py	feat: Add FP8 support for SM 120 (#3248)	2025-04-14 16:05:41 -07:00
image_processing.py	Update TensorRT-LLM (#2582)	2024-12-16 21:50:47 -08:00
layers.py	fix: Add missing parameter for WeightOnlyQuantRowLinear module (#2768)	2025-03-31 16:20:30 +08:00
mode.py	Fix fp8 kvcache (#3877)	2025-04-29 10:31:10 +08:00
quantize_by_modelopt.py	feat: adding multimodal (only image for now) support in trtllm-bench (#3490)	2025-04-18 07:06:16 +08:00
quantize.py	fix:update the default excluded_modules value for fp8rowwise recipe. (#3477)	2025-04-12 16:00:21 +08:00