[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
@@ -11,7 +11,6 @@ from vllm.model_executor.layers.attention.cross_attention import CrossAttention
from vllm.model_executor.layers.attention.encoder_only_attention import (
EncoderOnlyAttention,
)
from vllm.model_executor.layers.attention.mla_attention import MLAAttention
from vllm.model_executor.layers.attention.mm_encoder_attention import MMEncoderAttention
from vllm.model_executor.layers.attention.prefill_prefix_lm_attention import (
PrefillPrefixLMAttention,
@@ -35,7 +34,6 @@ __all__ = [
"ChunkedLocalAttention",
"CrossAttention",
"EncoderOnlyAttention",
"MLAAttention",
"MMEncoderAttention",
"PrefillPrefixLMAttention",
"RSWAAttention",
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff