[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
@@ -328,6 +328,13 @@ def test_apply_ready_response_syncs_block_size():
|
||||
vllm_version="test",
|
||||
world_size=1,
|
||||
data_parallel_size=1,
|
||||
tensor_parallel_size=1,
|
||||
pipeline_parallel_size=1,
|
||||
decode_context_parallel_size=1,
|
||||
data_parallel_rank=0,
|
||||
max_num_seqs=256,
|
||||
max_num_batched_tokens=8192,
|
||||
instance_id="test-instance",
|
||||
)
|
||||
)
|
||||
client._apply_ready_response(payload)
|
||||
|
||||
Reference in New Issue
Block a user