admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-07-23 09:46:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

rtc: exclude cold-start inference from latency tracker

Browse Source
This commit is contained in:
Maxime Ellerbach
2026-07-22 16:40:19 +00:00
parent 7845ee6f80
commit e0b50303aa
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/lerobot/rollout/inference/rtc.py
+4 -1
View File
@@ -252,6 +252,8 @@ class RTCInferenceEngine(InferenceEngine):
policy_device = torch.device(self._device)
warmup_required = max(1, self._compile_warmup_inferences) if self._use_torch_compile else 0
# exclude the first N inferences from the latency tracker to avoid cold-start spikes
latency_warmup_required = max(1, warmup_required)
inference_count = 0
consecutive_errors = 0
@@ -316,7 +318,8 @@ class RTCInferenceEngine(InferenceEngine):
inference_count += 1
consecutive_errors = 0
is_warmup = self._use_torch_compile and inference_count <= warmup_required
if is_warmup:
# Ignore the first N inferences for latency tracking to avoid cold-start spikes
if inference_count <= latency_warmup_required:
latency_tracker.reset()
else:
latency_tracker.add(new_latency)