[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:
2026-10-18 19:19:56 +07:00
co-authored by Hinata
parent c5ab42bc0f
commit e61dcb9143
2728 changed files with 159 additions and 950401 deletions
+8 -1
View File
@@ -121,7 +121,14 @@ def flashinfer_sampler_supported() -> bool:
"VLLM_USE_FLASHINFER_SAMPLER=0."
)
return False
from vllm.v1.attention.backends.flashinfer import FlashInferBackend
try:
from vllm.v1.attention.backends.flashinfer import FlashInferBackend
except ImportError:
logger.info_once(
"FlashInfer top-p/top-k sampling unavailable: "
"the FlashInfer attention backend is not installed."
)
return False
capability = current_platform.get_device_capability()
assert capability is not None