gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Use full state for frontier projection

Browse Source
This commit is contained in:
Gahow Wang
2026-06-29 16:22:09 +08:00
parent 8dd9ada194
commit 9ef9550214
2 changed files with 89 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
tests/test_core_flow.py
View File

@@ -2856,6 +2856,67 @@ class CoreFlowTests(unittest.TestCase):
},
},
),
TrialSummary(
trial_id="trial-0006",
status="completed",
parallel_size=4,
best_request_rate=8.0,
best_request_rate_per_gpu=2.0,
config_patch={
"env_patch": {},
"flag_patch": {
"tensor-parallel-size": 4,
"gpu-memory-utilization": 0.9,
"max-num-seqs": 16,
},
},
),
TrialSummary(
trial_id="trial-0007",
status="completed",
parallel_size=4,
best_request_rate=8.0,
best_request_rate_per_gpu=2.0,
config_patch={
"env_patch": {},
"flag_patch": {
"tensor-parallel-size": 4,
"gpu-memory-utilization": 0.92,
},
},
),
TrialSummary(
trial_id="trial-0008",
status="completed",
parallel_size=4,
best_request_rate=8.0,
best_request_rate_per_gpu=2.0,
config_patch={
"env_patch": {},
"flag_patch": {
"tensor-parallel-size": 4,
"gpu-memory-utilization": 0.9,
"max-num-batched-tokens": 16384,
"max-num-seqs": 16,
},
},
),
TrialSummary(
trial_id="trial-0009",
status="completed",
parallel_size=4,
best_request_rate=8.0,
best_request_rate_per_gpu=2.0,
config_patch={
"env_patch": {},
"flag_patch": {
"tensor-parallel-size": 4,
"gpu-memory-utilization": 0.9,
"enable-chunked-prefill": True,
"max-num-batched-tokens": 8192,
},
},
),
],
)
context = build_harness_context(