Update Dockerfile for vllm wheel version and enhance SHM connector tests
- Updated Dockerfile to use a new vllm wheel version. - Modified test_put_get_inline to clarify that it always uses SHM and updated metadata assertions. - Added handling for speculative configuration in GPU model runners to delay clearing connector metadata. - Refactored payload decoding in OmniGPUModelRunner for better clarity and maintainability. Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
1 parent
e22ae62396
commit
861698f88f
10 files changed
+169
-224
No files matched your search
@@ -64,14 +64,13 @@ def shm_connector():
|
||||
|
||||
|
||||
def test_put_get_inline(shm_connector):
|
||||
"""Test inline transfer for small data."""
|
||||
"""Test transfer for small data (currently always uses SHM)."""
|
||||
data = {"small": "data"}
|
||||
# Ensure data is smaller than threshold (100 bytes)
|
||||
|
||||
success, size, metadata = shm_connector.put("stage_0", "stage_1", "req_1", data)
|
||||
assert success is True
|
||||
assert "inline_bytes" in metadata
|
||||
assert "shm" not in metadata
|
||||
assert "shm" in metadata
|
||||
assert "size" in metadata
|
||||
|
||||
# Retrieve
|
||||
retrieved_data, ret_size = shm_connector.get("stage_0", "stage_1", "req_1", metadata)
|
||||
|
||||
Reference in new issue
Block a user