root
/
tabby
mirror of https://gitee.com/zhang_1334717033/tabby.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
tabby/crates/llama-cpp-bindings/Cargo.toml

22 lines
437 B
TOML
Raw Normal View History

feat: llama.cpp for metal support [TAB-146] (#391) * feat: init commit adding llama-cpp-bindings * add llama.cpp submodule * add LlamaEngine to hold llama context / llama model * add cxxbridge * add basic greedy sampling * move files * make compile success * connect TextGeneration with LlamaEngine * experimental support llama.cpp * add metal device * add Accelerate * fix namespace for llama-cpp-bindings * fix lint * move stepping logic to rust * add stop words package * use stop-words in ctranslate2-bindings * use raw string for regex * use Arc<Tokenizer> for sharing tokenizers * refactor: remove useless stop_words_encoding_offset * switch to tokenizers 0.13.4-rc.3 * fix lints in cpp * simplify implementation of greedy decoding * feat: split metal feature for llama backend * add ci * update ci * build tabby bin in ci build
2023-09-03 01:59:07 +00:00
[package]
name = "llama-cpp-bindings"
chore: release 0.5.0 (#697) * Release 0.5.0-rc.0 http-api-bindings@0.5.0-rc.0 llama-cpp-bindings@0.5.0-rc.0 tabby@0.5.0-rc.0 tabby-common@0.5.0-rc.0 tabby-download@0.5.0-rc.0 tabby-inference@0.5.0-rc.0 tabby-scheduler@0.5.0-rc.0 Generated by cargo-workspaces * fix: docker branch tag should only generate when not empty * Release 0.5.0-rc.1 http-api-bindings@0.5.0-rc.1 llama-cpp-bindings@0.5.0-rc.1 tabby@0.5.0-rc.1 tabby-common@0.5.0-rc.1 tabby-download@0.5.0-rc.1 tabby-inference@0.5.0-rc.1 tabby-scheduler@0.5.0-rc.1 Generated by cargo-workspaces * fix: handlebar syntax in meta action * Release 0.5.0-rc.2 http-api-bindings@0.5.0-rc.2 llama-cpp-bindings@0.5.0-rc.2 tabby@0.5.0-rc.2 tabby-common@0.5.0-rc.2 tabby-download@0.5.0-rc.2 tabby-inference@0.5.0-rc.2 tabby-scheduler@0.5.0-rc.2 Generated by cargo-workspaces * fix: handlebar syntax in meta action * Release 0.5.0-rc.3 http-api-bindings@0.5.0-rc.3 llama-cpp-bindings@0.5.0-rc.3 tabby@0.5.0-rc.3 tabby-common@0.5.0-rc.3 tabby-download@0.5.0-rc.3 tabby-inference@0.5.0-rc.3 tabby-scheduler@0.5.0-rc.3 Generated by cargo-workspaces * docs: update change log and docs * fix: collect_snippet should handle NotReady error * Release 0.5.0-rc.4 http-api-bindings@0.5.0-rc.4 llama-cpp-bindings@0.5.0-rc.4 tabby@0.5.0-rc.4 tabby-common@0.5.0-rc.4 tabby-download@0.5.0-rc.4 tabby-inference@0.5.0-rc.4 tabby-scheduler@0.5.0-rc.4 Generated by cargo-workspaces * Release 0.5.0 http-api-bindings@0.5.0 llama-cpp-bindings@0.5.0 tabby@0.5.0 tabby-common@0.5.0 tabby-download@0.5.0 tabby-inference@0.5.0 tabby-scheduler@0.5.0 Generated by cargo-workspaces
2023-11-04 01:02:03 +00:00
version = "0.5.0"
feat: llama.cpp for metal support [TAB-146] (#391) * feat: init commit adding llama-cpp-bindings * add llama.cpp submodule * add LlamaEngine to hold llama context / llama model * add cxxbridge * add basic greedy sampling * move files * make compile success * connect TextGeneration with LlamaEngine * experimental support llama.cpp * add metal device * add Accelerate * fix namespace for llama-cpp-bindings * fix lint * move stepping logic to rust * add stop words package * use stop-words in ctranslate2-bindings * use raw string for regex * use Arc<Tokenizer> for sharing tokenizers * refactor: remove useless stop_words_encoding_offset * switch to tokenizers 0.13.4-rc.3 * fix lints in cpp * simplify implementation of greedy decoding * feat: split metal feature for llama backend * add ci * update ci * build tabby bin in ci build
2023-09-03 01:59:07 +00:00
edition = "2021"
feat: switch cuda backend to llama.cpp (#656) * feat: switch cuda backend to llama.cpp * fix * fix
2023-10-27 20:41:22 +00:00
[features]
cuda = []
feat: llama.cpp for metal support [TAB-146] (#391) * feat: init commit adding llama-cpp-bindings * add llama.cpp submodule * add LlamaEngine to hold llama context / llama model * add cxxbridge * add basic greedy sampling * move files * make compile success * connect TextGeneration with LlamaEngine * experimental support llama.cpp * add metal device * add Accelerate * fix namespace for llama-cpp-bindings * fix lint * move stepping logic to rust * add stop words package * use stop-words in ctranslate2-bindings * use raw string for regex * use Arc<Tokenizer> for sharing tokenizers * refactor: remove useless stop_words_encoding_offset * switch to tokenizers 0.13.4-rc.3 * fix lints in cpp * simplify implementation of greedy decoding * feat: split metal feature for llama backend * add ci * update ci * build tabby bin in ci build
2023-09-03 01:59:07 +00:00
[build-dependencies]
cxx-build = "1.0"
cmake = "0.1"
[dependencies]
cxx = "1.0"
async-trait = { workspace = true }
tokio = { workspace = true, features = ["rt"] }
tabby-inference = { path = "../tabby-inference" }
derive_builder = { workspace = true }
feat: support cancellation in llama backend [TAB-146] (#392) * feat: support cancellation in llama backend * fix lint
2023-09-03 02:15:54 +00:00
tokio-util = { workspace = true }
feat: add /generate and /generate_streaming (#482) * feat: add generate_stream interface * extract engine::create_engine * feat add generate::generate * support streaming in llama.cpp * support streaming in ctranslate2 * update * fix formatting * refactor: extract helpers functions
2023-09-28 17:20:50 +00:00
futures.workspace = true
async-stream.workspace = true