[Frontend][Build] Add vllm download-kernels for FlashInfer precompiled kernels (#58765)

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Misha Goin
2026-10-09 21:22:35 -07:00
committed by GitHub
co-authored by Claude Opus 5.5
parent be0823357f
commit 29e4d2d42e
15 changed files with 309 additions and 20 deletions
+2
View File
@@ -73,6 +73,7 @@ from vllm.profiler.wrapper import (
from vllm.sequence import IntermediateTensors
from vllm.tasks import SupportedTask
from vllm.tracing import instrument
from vllm.utils.flashinfer import warn_if_flashinfer_kernels_missing
from vllm.utils.gc_utils import freeze_gc_heap, maybe_attach_gc_debug_callback
from vllm.utils.gpu_sync_debug import enable_gpu_sync_check, with_gpu_sync_check
from vllm.utils.mem_constants import GiB_bytes
@@ -497,6 +498,7 @@ class Worker(WorkerBase):
if self.use_v2_model_runner:
logger.info_once("Using V2 Model Runner")
warn_if_flashinfer_kernels_missing()
# Set random seed.
set_random_seed(self.model_config.seed)