Commit History

Автор SHA1 Съобщение Дата
  Georgi Gerganov 85a7d8677b memory : remove KV cache size padding (#16812) преди 2 месеца
  Georgi Gerganov d00cbea63c server : host-memory prompt caching (#16391) преди 3 месеца
  Johannes Gäßler e81b8e4b7f llama: use FA + max. GPU layers by default (#15434) преди 4 месеца
  Georgi Gerganov d2fcd91cf9 server : disable context shift by default (#15416) преди 5 месеца
  Xuan-Son Nguyen 6aa892ec2a server : do not return error out of context (with ctx shift disabled) (#13577) преди 8 месеца
  Diego Devesa 1d36b3670b llama : move end-user examples to tools directory (#13249) преди 8 месеца