Pai-Megatron-Patch is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named Pai-Megatron-Patch among their alternatives. The relationship is not symmetric — how Pai-Megatron-Patch rates them is a separate judgement, made when Pai-Megatron-Patch is analysed in its own right.
calls Pai-Megatron-Patch “Alibaba's patched Megatron stack for LLM/VLM training; choose it if you need its model recipes and multi-modal scale-out, while accepting Megatron-LM as the base.”
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries