A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 10:45 UTC
[CI/Build] Fix machete generated kernel files ordering (#8976)
Signed-off-by: kevin <kevin@anyscale.com> Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
Kevin H. Luu committed
Sep 30, 2024 at 20:33 UTC
aaccca2b4d3895d64d34b123e61731404c8fc2c0
1 file changed
+7
-1
csrc/quantization/machete/generate.py
+7
-1
@@ -457,7 +457,13 @@ def generate():
457
)),
458
]
459
460
- schedules = list(set([x[1] for x in default_heuristic]))
460
+ # Do not use schedules = list(set(...)) because we need to make sure
461
+ # the output list is deterministic; otherwise the generated kernel file
462
+ # will be non-deterministic and causes ccache miss.
463
+ schedules = []
464
+ for _, schedule_config in default_heuristic:
465
+ if schedule_config not in schedules:
466
+ schedules.append(schedule_config)
467
468
impl_configs = []
469