Popular repositories Loading

1. fineweb-edu-chinese fineweb-edu-chinese Public

   Python 34 4

2. sliding-window-attention-adaptation sliding-window-attention-adaptation Public

   Adapt full attention LLM to sliding window attention

   Python 14

3. parallel-decoding-in-one-sequence parallel-decoding-in-one-sequence Public

   Python 8

4. Combined_LLM Combined_LLM Public

   combine 2 LLM

   Python 6

5. hard_retrieval_for_llm hard_retrieval_for_llm Public

   hard long context retrieval tasks for language models

   Python 6

6. speculative_pipeline_decoding speculative_pipeline_decoding Public

   a new speculative decoding paradigm

   Python 6 1