quantizations
This commit is contained in:
@@ -17,6 +17,7 @@ from meshnet_tracker.auth import sign_hive_request
|
||||
from meshnet_tracker.server import (
|
||||
TrackerServer,
|
||||
_NodeEntry,
|
||||
_available_quantizations,
|
||||
_memory_pool_map,
|
||||
_registration_ban_error,
|
||||
_scale_demanded_models_locked,
|
||||
@@ -130,6 +131,48 @@ def test_tracker_lists_recommended_kimi_before_nodes_register():
|
||||
assert network_map["recommended_models"][0]["id"] == "kimi-k2.7"
|
||||
|
||||
|
||||
def test_tracker_lists_recommended_qwen_27b_before_nodes_register():
|
||||
"""Recommended Qwen 27B is advertised with its pinned canonical artifact.
|
||||
|
||||
Tags: http, routing, tracker
|
||||
"""
|
||||
tracker = TrackerServer()
|
||||
port = tracker.start()
|
||||
url = f"http://127.0.0.1:{port}"
|
||||
try:
|
||||
models = _get_json(f"{url}/v1/models")
|
||||
network_map = _get_json(f"{url}/v1/network/map")
|
||||
finally:
|
||||
tracker.stop()
|
||||
|
||||
qwen = next(model for model in models["data"] if model["id"] == "qwen3.6-27b")
|
||||
assert qwen["hf_repo"] == "Qwen/Qwen3.6-27B"
|
||||
assert qwen["revision"] == "6a9e13bd6fc8f0983b9b99948120bc37f49c13e9"
|
||||
assert qwen["metadata"]["num_layers"] == 64
|
||||
assert qwen["metadata"]["text_only"] is True
|
||||
assert qwen["deployment"]["recommended"] is True
|
||||
advertised = next(model for model in network_map["recommended_models"] if model["id"] == "qwen3.6-27b")
|
||||
assert advertised["hf_repo"] == "Qwen/Qwen3.6-27B"
|
||||
|
||||
|
||||
def test_quantization_coverage_uses_higher_precision_shards():
|
||||
"""A minimum-precision route may upgrade individual shards."""
|
||||
bf16 = _NodeEntry(
|
||||
"bf16", "http://node-a", 0, 0, "qwen3.6-27b", None, {}, None, 1.0,
|
||||
quantization="bfloat16",
|
||||
)
|
||||
int8 = _NodeEntry(
|
||||
"int8", "http://node-b", 1, 1, "qwen3.6-27b", None, {}, None, 1.0,
|
||||
quantization="int8",
|
||||
)
|
||||
|
||||
variants = {entry["id"]: entry for entry in _available_quantizations([bf16, int8], 0, 1)}
|
||||
|
||||
assert variants["bfloat16"]["selectable"] is False
|
||||
assert variants["int8"]["selectable"] is True
|
||||
assert variants["nf4"]["selectable"] is True
|
||||
|
||||
|
||||
def test_network_map_exposes_pool_size_and_speed_summary():
|
||||
"Network map exposes pool size and speed summary\n\nTags: http, routing, tracker"
|
||||
tracker = TrackerServer()
|
||||
|
||||
Reference in New Issue
Block a user