- llm
- training
- communication
- inference
•
•
•
-
Study on Batching
Orca notes
-
Tools
Tools Used Recently
-
Disaggregated Serving
notes on nvidia dynamo (framework for inference)
-
Study on vLLM
background notes on vllm
-
Inference Simulation Notes
Quotes from Papers that Hint at Significance of Communication in Inference
-
Study on LLM Inference Communication
background notes on llm inference communication
-
Study on LLM Inference
background notes on llm inference
-
NCCL Intra/Inter-Node Communication
understanding nccl intra/inter-node communication
-
LLM Training Optimization: Megatron and Deepspeed
notes on megatron and deepspeed
-
Survey on LLM Training Today
general notes on sota llm infrastructure
-
Parallelism in Distributed Training