Back to tags
Tag

Agent Skills with tag: Tensor

8 skills match this tag. Use tags to discover related Agent Skills and explore similar workflows.

distributed-training-megatron-core

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

[Megatron-CoreLarge-ScaleTrainingNVIDIA
Orchestra Research
Orchestra Research
33,1943,891

inference-serving-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

[vLLMInferenceServingPagedAttention
Orchestra Research
Orchestra Research
33,1943,891

model-architecture-torchtitan

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

[ModelArchitectureDistributedTraining
Orchestra Research
Orchestra Research
33,1943,891

serving-llms-vllm

vLLM: high-throughput LLM serving, OpenAI API, quantization.

[vLLMInferenceServingPagedAttention
delorenj
delorenj
176

serving-llms-vllm

vLLM: high-throughput LLM serving, OpenAI API, quantization.

[vLLMInferenceServingPagedAttention
poorrican
poorrican
0

distributed-llm-pretraining-torchtitan

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

[ModelArchitectureDistributedTraining
poorrican
poorrican
0

serving-llms-vllm

vLLM: high-throughput LLM serving, OpenAI API, quantization.

[vLLMInferenceServingPagedAttention
PoorRican
PoorRican
0

distributed-llm-pretraining-torchtitan

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

[ModelArchitectureDistributedTraining
PoorRican
PoorRican
0