llama.cpp
527b6fba - llama : make model stateless and context stateful (llama_state) (#1797)

Commit

2 years ago

llama : make model stateless and context stateful (llama_state) (#1797) * llama : make model stateless and context stateful * llama : minor cleanup * llama : update internal API declaration * Apply suggestions from code review fix style Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Missing model memory release * Fix style * Add deprecated warning for public API function llama_init_from_file * Update public API use cases: move away from deprecated llama_init_from_file * Deprecate public API function llama_apply_lora_from_file --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

References

#1797 - Make model stateless and context stateful (llama_state)

Author

didzis

Parents

d7b7484f

Files13

examples
- common.cpp
- common.h
- embedding
  - embedding.cpp
- main
  - main.cpp
- perplexity
  - perplexity.cpp
- quantize-stats
  - quantize-stats.cpp
- save-load-state
  - save-load-state.cpp
- server
  - server.cpp
- simple
  - simple.cpp
- train-text-from-scratch
  - train-text-from-scratch.cpp
llama.cpp
llama.h
tests
- test-tokenizer-0.cpp

llama.cpp 527b6fba - llama : make model stateless and context stateful (llama_state) (#1797)

llama.cpp
527b6fba - llama : make model stateless and context stateful (llama_state) (#1797)