[Rust Frontend][gRPC] Add server and model discovery (#49491)
Signed-off-by: Connor Carpenter <connorc@nvidia.com> Co-authored-by: Nick Hill <nickhill123@gmail.com>
This commit is contained in:
co-authored by
Nick Hill
parent
2b465b2c42
commit
e3c2fc3b3c
@@ -82,6 +82,13 @@ class EngineCoreReadyResponse:
|
||||
vllm_version: str
|
||||
world_size: int
|
||||
data_parallel_size: int
|
||||
tensor_parallel_size: int
|
||||
pipeline_parallel_size: int
|
||||
decode_context_parallel_size: int
|
||||
data_parallel_rank: int
|
||||
max_num_seqs: int
|
||||
max_num_batched_tokens: int
|
||||
instance_id: str
|
||||
# KV cache capacity (None for encoder-only/attention-free models).
|
||||
kv_cache_size_tokens: int | None = None
|
||||
kv_cache_max_concurrency: float | None = None
|
||||
|
||||
Reference in New Issue
Block a user