[Rust Frontend] Report vllm-proto schema version in ServerInfo (#61533)
Signed-off-by: Alec Flowers <aflowers@nvidia.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> Co-authored-by: Bugen Zhao <i@bugenzhao.com>
This commit is contained in:
co-authored by
Claude Opus 5.5
Bugen Zhao
parent
aa0c433a3e
commit
467b024f21
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "vllm-proto"
|
||||
version = "0.5.0"
|
||||
version = "0.6.0"
|
||||
edition.workspace = true
|
||||
license.workspace = true
|
||||
description = "Protobuf messages and gRPC bindings for the vLLM Rust frontend"
|
||||
|
||||
@@ -16,7 +16,7 @@ the schemas on pull requests, including on forks.
|
||||
|
||||
```toml
|
||||
[dependencies]
|
||||
vllm-proto = "0.5"
|
||||
vllm-proto = "0.6"
|
||||
```
|
||||
|
||||
For example, import `vllm_proto::inference_client::InferenceClient` or
|
||||
|
||||
@@ -54,6 +54,7 @@ message ServerInfo {
|
||||
uint64 max_batched_tokens = 9;
|
||||
uint32 max_loras = 10;
|
||||
RlCapabilities rl_capabilities = 11;
|
||||
string proto_version = 12;
|
||||
// Full-attention block size in tokens after initialization; absent if unavailable.
|
||||
optional uint64 effective_attention_block_size = 14;
|
||||
}
|
||||
|
||||
@@ -4,3 +4,6 @@
|
||||
//! Protobuf messages and gRPC clients and servers for vLLM's Inference and Control APIs.
|
||||
|
||||
tonic::include_proto!("vllm");
|
||||
|
||||
/// Schema version of this crate, reported by servers as `ServerInfo.proto_version`.
|
||||
pub const VERSION: &str = env!("CARGO_PKG_VERSION");
|
||||
|
||||
Reference in New Issue
Block a user