[Mini-vLLM] SM86-only cut: models, backends, Rust, tests
- Keep only Qwen3.5, Qwen3.5-MTP and Qwen4Exp model paths; trim the model registry to 41 entries - Delete idle attention backends (MLA, FlashInfer, ROCm-only, quant backends) and dead GDN CuTeDSL kernels - Remove inc/quark quant loaders; keep compressed-tensors and Marlin - Drop the Rust frontend, pooling entrypoints, and idle test suites - Rebuild kernels for sm_80;sm_86 and strip the extensions - Verified: full import sweep clean (optional deps only) and a dummy-load Qwen3.5 engine run on RTX 3090 via the Triton GDN path Co-authored-by: Hinata <hinata@idihore.id> Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
@@ -40,7 +40,6 @@ def main():
|
||||
if maybe_run_omni():
|
||||
return
|
||||
|
||||
import vllm.entrypoints.cli.benchmark.main
|
||||
import vllm.entrypoints.cli.collect_env
|
||||
import vllm.entrypoints.cli.download_kernels
|
||||
import vllm.entrypoints.cli.launch
|
||||
@@ -59,7 +58,6 @@ def main():
|
||||
vllm.entrypoints.cli.openai,
|
||||
vllm.entrypoints.cli.serve,
|
||||
vllm.entrypoints.cli.launch,
|
||||
vllm.entrypoints.cli.benchmark.main,
|
||||
vllm.entrypoints.cli.collect_env,
|
||||
vllm.entrypoints.cli.download_kernels,
|
||||
vllm.entrypoints.cli.preload,
|
||||
@@ -70,24 +68,6 @@ def main():
|
||||
if sys.argv[1:2] != ["snapshot"]:
|
||||
cli_env_setup()
|
||||
|
||||
vllm.entrypoints.cli.benchmark.main.maybe_exec_rust_bench()
|
||||
|
||||
# For 'vllm bench *': use CPU instead of UnspecifiedPlatform by default
|
||||
if len(sys.argv) > 1 and sys.argv[1] == "bench":
|
||||
logger.debug(
|
||||
"Bench command detected, must ensure current platform is not "
|
||||
"UnspecifiedPlatform to avoid device type inference error"
|
||||
)
|
||||
from vllm import platforms
|
||||
|
||||
if platforms.current_platform.is_unspecified():
|
||||
from vllm.platforms.cpu import CpuPlatform
|
||||
|
||||
platforms.current_platform = CpuPlatform()
|
||||
logger.info(
|
||||
"Unspecified platform detected, switching to CPU Platform instead."
|
||||
)
|
||||
|
||||
parser = FlexibleArgumentParser(
|
||||
description="vLLM CLI",
|
||||
epilog=VLLM_SUBCMD_PARSER_EPILOG.format(subcmd="[subcommand]"),
|
||||
|
||||
Reference in New Issue
Block a user