Activity
Merge branch 'main' into misc_fixes
Merge branch 'main' into misc_fixes
Use MutableTorchTensorRTModule to do quantization
Use MutableTorchTensorRTModule to do quantization
Fixed the benchmark typo
Fixed the benchmark typo
Force push
Fixed the benchmark typo
Fixed the benchmark typo
Force push
Fixed the benchmark typo
Fixed the benchmark typo
Force push
Fixed the benchmark typo
Fixed the benchmark typo
Force push
chore(deps): bump transformers from 4.48.0 to 4.50.0 in /examples/dynamo
chore(deps): bump transformers from 4.48.0 to 4.50.0 in /examples/dynamo
Force push
19 hours ago
chore: update the docstring for llama2 rmsnorm automatic plugin example
chore: update the docstring for llama2 rmsnorm automatic plugin example
correcting the non critical lint error
correcting the non critical lint error
Use dllist on linux to check cross compile feature
Use dllist on linux to check cross compile feature
Force push
Use dllist on linux to check cross compile feature
Use dllist on linux to check cross compile feature
Force push
Use dllist on linux to check cross compile feature
Use dllist on linux to check cross compile feature
Force push
Use dllist on linux to check cross compile feature
Use dllist on linux to check cross compile feature
CI error for not stating reason in unittest skip
CI error for not stating reason in unittest skip
Force push
feat: implement static/dynamic kv cache in Torch-TRT
feat: implement static/dynamic kv cache in Torch-TRT
restructure the dynamic double quantize and static double quantize code
restructure the dynamic double quantize and static double quantize code
add nvidia-modelopt python version dependency
add nvidia-modelopt python version dependency