feat(p800): auto-load timing module in every TP worker process
sitecustomize.py is imported automatically by Python at startup in every process, including the SGLang scheduler/TP worker processes spawned for tensor parallelism. Adding the p800_timing import here ensures the monkey-patches are applied to all 8 TP workers, not just the launch_server parent process (which never runs the model forward and would record empty timing data). The timing module self-disables unless SGLANG_TIMING_ENABLED=1, so this import is a no-op when timing is not in use. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
parent
f81c647d16
commit
bf03201168
@ -5,3 +5,6 @@ import torch
|
||||
# them on P800 via its own FP8 kernels.
|
||||
if not hasattr(torch, "float8_e8m0fnu"):
|
||||
torch.float8_e8m0fnu = torch.uint8
|
||||
|
||||
# P800 Timing module
|
||||
import p800_timing
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user