linear-attention
Tracked open-source repos tagged linear-attention, sorted by stars.
Related topics
Topics that frequently appear alongside linear-attention on the same repo.
Recent risers
Repos created in the last 90 days, tagged linear-attention.
- #1
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
★ 7,187
- #1
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
★ 14,695+8Star change over the last 7 days - #2
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
★ 7,187+468Star change over the last 7 days
