b8zhong 77225d602a Use Flashinfer TRT-LLM as Llama 4 compatible MoE backend (#11928)

2025-10-28 10:39:43 -07:00

..

__init__.py

Enable native ModelOpt quantization support (1/3) (#7149)

2025-10-06 13:24:15 -07:00

loader.py

Add AWQ quantization support for NPU. (#10158)

2025-10-23 12:08:05 -07:00

remote_instance_weight_loader_utils.py

refactor loading weights from remote instance coding format (#10941)

2025-09-26 15:25:39 -07:00

utils.py

model: support deepseek-ocr (#11891)

2025-10-24 03:15:17 +08:00

weight_utils.py

Use Flashinfer TRT-LLM as Llama 4 compatible MoE backend (#11928)

2025-10-28 10:39:43 -07:00