tllama 0.1.1

Lightweight Local LLM Inference Engine
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127

[[bin]]
name = "tllama"
path = "src/main.rs"

[dependencies.actix-web]
optional = true
version = "4.11.0"

[dependencies.anyhow]
version = "1.0.100"

[dependencies.async-trait]
version = "0.1.89"

[dependencies.clap]
features = ["derive", "env"]
version = "4.5.47"

[dependencies.colored]
optional = true
version = "3.0.0"

[dependencies.ctrlc]
features = ["termination"]
optional = true
version = "3.5.0"

[dependencies.dirs]
version = "6.0.0"

[dependencies.encoding_rs]
version = "0.8.35"

[dependencies.gotpl]
optional = true
version = "0.2.3"

[dependencies.gtmpl-moyan]
optional = true
version = "0.7.1"

[dependencies.lazy_static]
version = "1.5.0"

[dependencies.llama-cpp-2]
default-features = false
features = ["openmp"]
optional = true
version = "0.1.121"

[dependencies.minijinja]
optional = true
version = "0.22.0"

[dependencies.rustyline]
optional = true
version = "17.0.1"

[dependencies.serde]
features = ["derive"]
version = "1.0.225"

[dependencies.serde_json]
version = "1.0.145"

[dependencies.tempfile]
optional = true
version = "3.23.0"

[dependencies.tokio]
features = ["rt-multi-thread", "macros"]
version = "1.47.1"

[dependencies.tokio-stream]
optional = true
version = "0.1.17"

[dependencies.tracing]
version = "0.1.41"

[dependencies.tracing-subscriber]
features = ["env-filter"]
version = "0.3.20"

[dependencies.uuid]
features = ["v4"]
optional = true
version = "1.18.1"

[dependencies.walkdir]
version = "2.5.0"

[features]
api = ["actix-web", "tokio-stream", "uuid"]
chat = ["rustyline", "colored", "ctrlc"]
default = ["tpl-gtmpl", "engine-llama-cpp", "api", "chat"]
engine-hf = ["tempfile"]
engine-llama-cpp = ["llama-cpp-2"]
hw-cuda = ["llama-cpp-2/cuda"]
hw-metal = ["llama-cpp-2/metal"]
hw-native = ["llama-cpp-2/native"]
hw-vulkan = ["llama-cpp-2/vulkan"]
tpl-gotpl = ["gotpl"]
tpl-gtmpl = ["gtmpl-moyan"]
tpl-minijinja = ["minijinja"]

[lib]
name = "tllama"
path = "src/lib.rs"

[package]
authors = ["moyan <moyan@moyanjdc.top>"]
autobenches = false
autobins = false
autoexamples = false
autolib = false
autotests = false
build = false
description = "Lightweight Local LLM Inference Engine"
documentation = "https://docs.rs/crate/tllama"
edition = "2024"
include = ["Cargo.toml", "src/**/*", "/README.md", "/LICENSE"]
license = "MIT"
name = "tllama"
readme = "README.md"
repository = "https://github.com/moyanj/tllama"
version = "0.1.1"