[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
@@ -216,6 +216,7 @@ impl pb::control_server::Control for ControlServiceImpl {
|
||||
max_batched_tokens: ready.max_num_batched_tokens,
|
||||
max_loras: ready.max_loras,
|
||||
rl_capabilities: Some(self.rl_capabilities()),
|
||||
proto_version: pb::VERSION.to_string(),
|
||||
effective_attention_block_size: self.client().effective_attention_block_size(),
|
||||
}))
|
||||
}
|
||||
|
||||
@@ -2013,6 +2013,7 @@ async fn control_reports_server_and_model_info() {
|
||||
assert_eq!(server.engine_version, "test-vllm-version");
|
||||
assert_eq!(server.effective_attention_block_size, Some(64));
|
||||
assert_eq!(server.api_version, "vllm");
|
||||
assert_eq!(server.proto_version, pb::VERSION);
|
||||
assert_eq!(server.instance_id, "test-instance");
|
||||
assert_eq!(server.max_model_len, DEFAULT_MOCK_MAX_MODEL_LEN as u32);
|
||||
assert_eq!(server.kv_block_size, DEFAULT_MOCK_BLOCK_SIZE as u32);
|
||||
|
||||
Reference in New Issue
Block a user