mawei/IQ.Pilot
2
0
Fork 0
mirror of https://gitlvb.teallvbs.xyz/IQ.Lvbs/IQ.Pilot.git synced 2026-08-07 14:35:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

IQ.Pilot Release Commit @ d23c019

Browse Source
This commit is contained in:
IQ.Lvbs CI [bot]
2026-07-26 18:52:41 -05:00
parent e557c3d8ee
commit 152206f935
262 changed files with 12479 additions and 11377 deletions
Download Patch File Download Diff File Expand all files Collapse all files
selfdrive/modeld/SConscript
+1 -1
View File
@@ -60,7 +60,7 @@ def host_tinygrad_flags(*, float16=False):
return f"{base} FLOAT16=1" if float16 else base
# Compile small models
for model_name in ['dmonitoring_model']:
for model_name in ['dmonitoring_model', 'dmonitoring_model_mici']:
# The optimization flags are mandatory on QCOM: without FLOAT16/NOLOCALS/JIT_BATCH_SIZE/OPENPILOT_HACKS these
# models compile to unoptimized QCOM kernels and run ~20x slower (dmonitoring_model: ~300ms -> ~14ms),
# which starves the driving model on the shared Adreno. IMAGE=2 (not upstream's IMAGE=1) because the