vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
llama.cpp/examples/batched.swift
History
Georgi Gerganov 0e89203b51
speculative : add tree-based sampling example (#3624) 
* sampling : one sequence per sampling context

ggml-ci

* speculative : add tree-based sampling support

ggml-ci

* speculative : reuse the n_parallel CLI param

* speculative : refactor sampling

* examples : fix build after sampling refactoring

ggml-ci

* batched : fix n_seq_id

* sampling : fix malloc

ggml-ci

* swift : fix build

ggml-ci

* swift : try to fix build

ggml-ci

* prompts : add assistant.txt

* common : add llama_batch_add() and llama_batch_clear() helpers

* speculative : minor refactor

ggml-ci

* minor : comments + rename

ggml-ci

* speculative : fix off-by-one for n_drafted

* speculative : fix the n_drafted fix + p constants
2023-10-18 16:21:57 +03:00
..
Sources speculative : add tree-based sampling example (#3624) 2023-10-18 16:21:57 +03:00
.gitignore examples : add batched.swift + improve CI for swift (#3562) 2023-10-11 06:14:05 -05:00
Makefile examples : add batched.swift + improve CI for swift (#3562) 2023-10-11 06:14:05 -05:00
Package.swift examples : add batched.swift + improve CI for swift (#3562) 2023-10-11 06:14:05 -05:00
README.md examples : add batched.swift + improve CI for swift (#3562) 2023-10-11 06:14:05 -05:00

README.md

This is a swift clone of examples/batched.

$ make $ ./swift MODEL_PATH [PROMPT] [PARALLEL]