"git@developer.sourcefind.cn:zhaoyu6/sglang.git" did not exist on "770529a73172499a4d3e6135b1c63f70d63e1f5d"
mod.rs 2.64 KB
Newer Older
Olivier Dehaene's avatar
v0.1.0  
Olivier Dehaene committed
1
//! Text Generation gRPC client library
Olivier Dehaene's avatar
Init  
Olivier Dehaene committed
2

OlivierDehaene's avatar
OlivierDehaene committed
3
use async_trait::async_trait;
Olivier Dehaene's avatar
Init  
Olivier Dehaene committed
4
use thiserror::Error;
Olivier Dehaene's avatar
v0.1.0  
Olivier Dehaene committed
5
use tonic::transport;
Olivier Dehaene's avatar
Init  
Olivier Dehaene committed
6
7
use tonic::Status;

Nicolas Patry's avatar
Nicolas Patry committed
8
9
10
11
12
13
14
15
16
17
18
19
20
#[allow(clippy::derive_partial_eq_without_eq)]
mod pb;

mod grpc_client;
mod sharded_client;

pub use grpc_client::Client;
pub use pb::generate::v3::{
    input_chunk::Chunk, Batch, CachedBatch, FinishReason, GeneratedText, Generation, GrammarType,
    HealthResponse, Image, InfoResponse, Input, InputChunk, NextTokenChooserParameters, Request,
    StoppingCriteriaParameters,
};
pub use sharded_client::ShardedClient;
OlivierDehaene's avatar
OlivierDehaene committed
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40

#[async_trait]
pub trait Health {
    /// Check if a generate server is healthy by asking it to allocate a tensor on device
    async fn device_health(&self) -> Result<()>;

    /// Check if a generate server is healthy by doing a forward pass.
    /// EXPENSIVE
    async fn model_health(&self) -> Result<()>;
}

#[derive(Debug)]
pub struct ShardInfo {
    pub requires_padding: bool,
    pub dtype: String,
    pub device_type: String,
    pub window_size: Option<u32>,
    pub speculate: u32,
}

Olivier Dehaene's avatar
Init  
Olivier Dehaene committed
41
#[derive(Error, Debug, Clone)]
Olivier Dehaene's avatar
Olivier Dehaene committed
42
pub enum ClientError {
43
    #[error("Could not connect to Text Generation server: {0}")]
Olivier Dehaene's avatar
Olivier Dehaene committed
44
    Connection(String),
45
    #[error("Server error: {0}")]
Olivier Dehaene's avatar
Olivier Dehaene committed
46
    Generation(String),
47
48
    #[error("Sharded results are empty")]
    EmptyResults,
Olivier Dehaene's avatar
Init  
Olivier Dehaene committed
49
50
51
52
}

impl From<Status> for ClientError {
    fn from(err: Status) -> Self {
53
54
55
        let err = Self::Generation(err.message().to_string());
        tracing::error!("{err}");
        err
Olivier Dehaene's avatar
Olivier Dehaene committed
56
57
58
59
60
    }
}

impl From<transport::Error> for ClientError {
    fn from(err: transport::Error) -> Self {
61
62
63
        let err = Self::Connection(err.to_string());
        tracing::error!("{err}");
        err
Olivier Dehaene's avatar
Init  
Olivier Dehaene committed
64
65
66
    }
}

67
68
69
70
71
72
73
// Small convenience re-wrapping of `Chunk`.
impl From<Chunk> for InputChunk {
    fn from(chunk: Chunk) -> Self {
        InputChunk { chunk: Some(chunk) }
    }
}

OlivierDehaene's avatar
OlivierDehaene committed
74
75
76
static WARMUP_IMAGE_BASE64 :&str = "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";

pub type Result<T> = std::result::Result<T, ClientError>;