llama.cpp
6e08281e - Extend llama_kv_cache_seq_rm to allow matching any sequence (#3843)
Commit
View On GitHub
Commit
1 year ago
Extend llama_kv_cache_seq_rm to allow matching any sequence (#3843) * Extend llama_kv_cache_seq_rm to allow matichng any sequence * Replace llama_kv_cache_tokens_rm with llama_kv_cache_clear Use llama_kv_cache_clear for cache clearing Change calls to llama_kv_cache_tokens_rm that want to delete by position to use llama_kv_cache_seq_rm functionality
Author
KerfuffleV2 KerfuffleV2
Parents
2046eb43
  • common
    • File
      common.cpp
  • examples
    • batched-bench
      • File
        batched-bench.cpp
    • llama-bench
      • File
        llama-bench.cpp
    • main
      • File
        main.cpp
    • perplexity
      • File
        perplexity.cpp
    • server
      • File
        server.cpp
  • File
    llama.cpp
  • File
    llama.h
FAQ Terms Privacy Refunds Impressum