[Rust Frontend] Move code from vllm-frontend-rs (#43283)
Signed-off-by: Bugen Zhao <i@bugenzhao.com> Signed-off-by: Nick Hill <nickhill123@gmail.com> Signed-off-by: Eric Curtin <eric.curtin@docker.com> Signed-off-by: Dev-X25874 <283057883+Dev-X25874@users.noreply.github.com> Signed-off-by: Will.hou <1205157517@qq.com> Signed-off-by: Will.hou <willamhou@ceresman.com> Co-authored-by: Nick Hill <nickhill123@gmail.com> Co-authored-by: Eric Curtin <eric.curtin@docker.com> Co-authored-by: Dev-X25874 <283057883+Dev-X25874@users.noreply.github.com> Co-authored-by: Will.hou <1205157517@qq.com> Co-authored-by: Will.hou <willamhou@ceresman.com> Please see https://github.com/Inferact/vllm-frontend-rs for full original commit history.
This commit is contained in:
co-authored by
Nick Hill
Eric Curtin
Dev-X25874
Will.hou
Will.hou
parent
39d5fa96a7
commit
39910f2b25
+129
@@ -0,0 +1,129 @@
|
||||
[workspace]
|
||||
members = [
|
||||
"src/chat",
|
||||
"src/cmd",
|
||||
"src/engine-core-client",
|
||||
"src/llm",
|
||||
"src/managed-engine",
|
||||
"src/metrics",
|
||||
"src/reasoning-parser",
|
||||
"src/server",
|
||||
"src/text",
|
||||
"src/tokenizer",
|
||||
"src/tool-parser",
|
||||
]
|
||||
resolver = "3"
|
||||
|
||||
[workspace.package]
|
||||
version = "0.1.0"
|
||||
edition = "2024"
|
||||
license = "Apache-2.0"
|
||||
|
||||
[workspace.dependencies]
|
||||
anyhow = "1.0.100"
|
||||
arc-swap = "1.9.0"
|
||||
async-openai = "0.33.1"
|
||||
async-trait = "0.1.89"
|
||||
asynk-strim-attr = "0.1.0"
|
||||
axum = "0.8.8"
|
||||
base64 = "0.22.1"
|
||||
bytemuck = { version = "1.25.0", features = ["extern_crate_alloc"] }
|
||||
byteorder = "1.5.0"
|
||||
bytes = "1.11.1"
|
||||
clap = { version = "4.5.38", features = ["derive", "env"] }
|
||||
criterion = "0.5.1"
|
||||
easy-ext = "1.0.3"
|
||||
educe = "0.6.0"
|
||||
enum-as-inner = "0.7.0"
|
||||
expect-test = "1.5.1"
|
||||
fastokens = "0.2.0"
|
||||
futures = "0.3.31"
|
||||
half = { version = "2.7.1", features = ["bytemuck"] }
|
||||
hex = "0.4.3"
|
||||
hf-hub = { version = "0.5.0", features = ["tokio"] }
|
||||
http-body = "1.0.1"
|
||||
itertools = "0.14.0"
|
||||
libc = "0.2.177"
|
||||
llm-multimodal = { git = "https://github.com/vllm-project/llm-multimodal", rev = "5b558989844d1c7af3e43d0f604069ffd9c06320" }
|
||||
minijinja = { version = "2.0", features = ["unstable_machinery", "json", "builtins", "loader", "loop_controls"] }
|
||||
minijinja-contrib = { version = "2.0", features = ["pycompat"] }
|
||||
native-tls-vendored = { package = "native-tls", version = "0.2.18", features = ["vendored"] }
|
||||
ndarray = { version = "0.16.1", features = ["serde"] }
|
||||
openai-harmony = "0.0.8"
|
||||
openai-protocol = "1.6.0"
|
||||
parking_lot = "0.12.5"
|
||||
prometheus-client = "0.24.0"
|
||||
prometheus-client-derive-encode = "0.5.0"
|
||||
prost = "0.14.3"
|
||||
prost-types = "0.14.3"
|
||||
reasoning-parser = "1.2.2"
|
||||
reqwest = { version = "0.12.8", default-features = false, features = ["rustls-tls"] }
|
||||
riptoken = { version = "0.3.0", default-features = false }
|
||||
rmp-serde = "1.3.1"
|
||||
rmpv = { version = "1.3.1", features = ["with-serde"] }
|
||||
rustc-hash = "1.1.0"
|
||||
serde = { version = "1.0.228", features = ["derive"] }
|
||||
serde-json-fmt = "0.1.0"
|
||||
serde_default = "0.2.0"
|
||||
serde_json = "1.0.145"
|
||||
serde_repr = "0.1.20"
|
||||
serde_tuple = "1.1.3"
|
||||
serde_with = "3.18.0"
|
||||
serial_test = "3.2.0"
|
||||
socket2 = "0.6.3"
|
||||
subenum = "1.1.3"
|
||||
task-local = "0.1.1"
|
||||
tekken = { package = "tekken-rs", version = "0.1.1", default-features = false }
|
||||
tempfile = "3.23.0"
|
||||
thiserror = "2.0.16"
|
||||
thiserror-ext = "0.3.0"
|
||||
tiktoken-rs = "0.9.1"
|
||||
time = { version = "0.3.47", features = ["formatting", "local-offset", "macros"] }
|
||||
tokenizers = "0.22.0"
|
||||
tokio = { version = "1.47.1", features = [
|
||||
"macros",
|
||||
"net",
|
||||
"rt-multi-thread",
|
||||
"sync",
|
||||
"time",
|
||||
] }
|
||||
tokio-stream = "0.1"
|
||||
tokio-util = { version = "0.7.18", features = ["rt"] }
|
||||
tonic = "0.14.5"
|
||||
tonic-build = "0.14.5"
|
||||
tonic-prost = "0.14.5"
|
||||
tonic-prost-build = "0.14.5"
|
||||
tool-parser = "1.2.0"
|
||||
tower = { version = "0.5.3", features = ["util"] }
|
||||
tower-http = { version = "0.6.8", features = ["trace"] }
|
||||
tracing = { version = "0.1.44", features = ["release_max_level_debug"] }
|
||||
tracing-futures = { version = "0.2.5", features = ["futures-03"] }
|
||||
tracing-subscriber = { version = "0.3.20", features = ["env-filter", "fmt"] }
|
||||
trait-set = "0.3.0"
|
||||
uuid = { version = "1.22.0", features = ["v4"] }
|
||||
validator = { version = "0.20.0", features = ["derive"] }
|
||||
vllm-chat = { path = "src/chat" }
|
||||
vllm-engine-core-client = { path = "src/engine-core-client" }
|
||||
vllm-llm = { path = "src/llm" }
|
||||
vllm-managed-engine = { path = "src/managed-engine" }
|
||||
vllm-metrics = { path = "src/metrics" }
|
||||
vllm-reasoning-parser = { path = "src/reasoning-parser" }
|
||||
vllm-server = { path = "src/server" }
|
||||
vllm-text = { path = "src/text" }
|
||||
vllm-tokenizer = { path = "src/tokenizer" }
|
||||
vllm-tool-parser = { path = "src/tool-parser" }
|
||||
winnow = "1.0.2"
|
||||
zeromq = { version = "0.6.0", default-features = false, features = [
|
||||
"tokio-runtime",
|
||||
"all-transport",
|
||||
] }
|
||||
|
||||
[workspace.lints.clippy]
|
||||
too_many_arguments = "allow"
|
||||
|
||||
[profile.dev]
|
||||
panic = "abort"
|
||||
|
||||
[profile.release]
|
||||
lto = "thin"
|
||||
panic = "abort"
|
||||
Reference in New Issue
Block a user