atomr-infer-runtime-tensorrt 0.8.0

TensorRT runner for atomr-infer. Wraps atomr-accel-tensorrt's TrtRuntime / ExecutionContext / ExecutionBindings behind the ModelRunner trait.
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

# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
#
# When uploading crates to the registry Cargo will automatically
# "normalize" Cargo.toml files for maximal compatibility
# with all versions of Cargo and also rewrite `path` dependencies
# to registry (e.g., crates.io) dependencies.
#
# If you are reading this file be aware that the original Cargo.toml
# will likely look very different (and much more reasonable).
# See Cargo.toml.orig for the original contents.

[package]
edition = "2021"
rust-version = "1.78"
name = "atomr-infer-runtime-tensorrt"
version = "0.8.0"
authors = ["atomr-infer contributors"]
build = false
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "TensorRT runner for atomr-infer. Wraps atomr-accel-tensorrt's TrtRuntime / ExecutionContext / ExecutionBindings behind the ModelRunner trait."
homepage = "https://github.com/rustakka/atomr-infer"
documentation = "https://docs.rs/atomr-infer-runtime-tensorrt"
readme = "README.md"
keywords = [
    "llm",
    "inference",
    "atomr",
    "actor",
    "openai",
]
categories = [
    "concurrency",
    "asynchronous",
    "science",
]
license = "Apache-2.0"
repository = "https://github.com/rustakka/atomr-infer"

[features]
default = []
tensorrt = [
    "dep:atomr-accel-tensorrt",
    "dep:cudarc",
    "dep:parking_lot",
]
tensorrt-fp8 = [
    "tensorrt",
    "atomr-accel-tensorrt/tensorrt-fp8",
]
tensorrt-int8 = [
    "tensorrt",
    "atomr-accel-tensorrt/tensorrt-int8",
]
tensorrt-link = [
    "tensorrt",
    "atomr-accel-tensorrt/tensorrt-link",
]
tensorrt-onnx = [
    "tensorrt",
    "atomr-accel-tensorrt/tensorrt-onnx",
]
tensorrt-plugin = [
    "tensorrt",
    "atomr-accel-tensorrt/tensorrt-plugin",
]

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

[dependencies.async-trait]
version = "0.1"

[dependencies.atomr-accel-tensorrt]
version = "0.10.0"
optional = true

[dependencies.atomr-infer-core]
version = "0.8.0"

[dependencies.atomr-infer-runtime]
version = "0.8.0"

[dependencies.cudarc]
version = "0.19.4"
features = [
    "cuda-version-from-build-system",
    "fallback-latest",
]
optional = true

[dependencies.parking_lot]
version = "0.12"
optional = true

[dependencies.serde]
version = "1"
features = ["derive"]

[dependencies.tracing]
version = "0.1"

[dev-dependencies.tempfile]
version = "3"

[dev-dependencies.tokio]
version = "1.39"
features = [
    "full",
    "macros",
    "rt",
]