NeMo Framework Megatron Backend

NVIDIA

Container

NVIDIA

NeMo Framework Megatron Backend

NVIDIA NeMo™ framework Megatron backend supports pre-training, post-training, and reinforcement learning of LLMs and multi-modal generative AI models with state-of-the-art data processing, model training techniques, and flexible deployment options.

NVIDIA AI Enterprise Supported

Layer	Label		Created
1343f9fc9f333801b88044877d270134caaf433b3e4f066d69b9ef44a634ecdc	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace; ExposedPorts 6006/tcp, 8888/tcp`	02/21/2024 4:31 AM UTC
28c5be5058030cb86b36155b3ef7ae74c4d991c711c3b64d66fa17efc459196a	ARG	`NVIDIA_BUILD_REF`	02/21/2024 4:31 AM UTC
25aa90c6e50bca16b63b0a0d83013a26522e9ec3343639e5583ee1cb542275b3	LABEL	`com.nvidia.build.id=80741402`	02/21/2024 4:31 AM UTC
3fc8c676fb929ad54515cc35817bd2bd9cad0462162ced558299b79040fb2792	ENV	`NVIDIA_BUILD_ID=80741402`	02/21/2024 4:31 AM UTC
5d0d25e8c1cf4c186cfae26b55a92cbd77d25ac631e7765f7573a3323e813007	ARG	`NVIDIA_BUILD_ID`	02/21/2024 4:31 AM UTC
1cd2218257ece74ef661ae1a3c4be09f246838dc518b08071d8f2f395d9dbbfa	ENV	`NVTE_APPLY_QK_LAYER_SCALING=0`	02/21/2024 4:31 AM UTC
b00f8a5371e0ccc74ee29c10c2e2c0cb985868f682c43e69e98cc660aa4993cd	RUN	`chmod -R a+w /workspace`	02/21/2024 4:31 AM UTC
f6656a6661e90e7954d79d3982359785ce4fd657911bd3fafb347ea6b792df2a	COPY	`sequence_packing sequence_packing`	02/21/2024 4:31 AM UTC
d71dd246c90dff5a5c7b78eb8ed38e6a1148c1fef52535a723aa9fc5f4f68e88	WORKDIR	`/workspace`	02/21/2024 4:31 AM UTC
709d25deaa3fb85ce4f360840b58cb3ba9c18b0b14c98cb27aa2caf596f5b310	RUN	`rm -r /tmp/inflight_batcher_llm && rm -r /tmp/tensorrt_llm`	02/21/2024 4:31 AM UTC