Skip to content
Snippets Groups Projects
GitSwiftDev's avatar
GitSwiftDev's avatar
GitSwiftDev's avatar
  • 0faf3bf1 · CacheCraft: A Relevant Work on Chunk-Aware KV Cache Reuse for RAG (...
GitSwiftDev's avatar
  • eb7e0d01 · Update DeepSeek/MLA Topics (#125)
GitSwiftDev's avatar
  • 99280223 · Add DeepSeek Open Sources modules (#124)
GitSwiftDev's avatar
  • d32b3dde · update the title of SageAttention2 and add SpargeAttn (#123)
GitSwiftDev's avatar
  • cc978444 · 🔥[MHA2MLA] Towards Economical Inference: Enabling DeepSeek’s Multi-...
GitSwiftDev's avatar
  • 4cb87630 · Add our ICLR2025 work Dynamic-LLaVA (#121)
GitSwiftDev's avatar
GitSwiftDev's avatar
  • 0525c4d4 · 🔥[DeepSeek-NSA] Native Sparse Attention: Hardware-Aligned and Nativ...
GitSwiftDev's avatar
GitSwiftDev's avatar
  • 1ddf093b · Add Multi-head Latent Attention(MLA) topic (#118)
GitSwiftDev's avatar
GitSwiftDev's avatar
GitSwiftDev's avatar
GitSwiftDev's avatar
  • b117b3c1 · [feat] add deepseek-r1 (#113)
GitSwiftDev's avatar
GitSwiftDev's avatar
GitSwiftDev's avatar
GitSwiftDev's avatar