ef6abf3dc7
Adds ALL files needed for Dockerfile build:
- qwen3_6_scripts/ (baseline patches + our optimizations)
- vllm/ (full vllm package)
- paged_attention_v2_pytorch.py (V2 with single-bmm optimization)
- Dockerfile + computility-run.yaml
Our optimizations vs baseline:
1. paged_attn.py: pre-gathered context KV (eliminates 194 gather calls),
Triton try/fallback, V2 heuristic, threshold 32K→64K
2. paged_attention_v2_pytorch.py: fills NotImplementedError,
single-bmm Phase 1 (195 launches → 3)
3. patch_enable_triton.py: HAS_TRITON=True with safety fallback
4. patch_triton_tuning.py: BLOCK=64, NUM_WARPS=4 for BI-V100
5. computility-run.yaml: gpu-memory-utilization 0.9→0.95,
max-num-batched-tokens 8192→16384
This repo can now be submitted to dev.modelhub.org.cn as-is.
23 lines
756 B
Python
23 lines
756 B
Python
from .interfaces import (HasInnerState, SupportsLoRA, SupportsMultiModal,
|
|
SupportsPP, has_inner_state, supports_lora,
|
|
supports_multimodal, supports_pp)
|
|
from .interfaces_base import (VllmModelForEmbedding,
|
|
VllmModelForTextGeneration, is_embedding_model,
|
|
is_text_generation_model)
|
|
from .registry import ModelRegistry
|
|
|
|
__all__ = [
|
|
"ModelRegistry",
|
|
"VllmModelForEmbedding",
|
|
"is_embedding_model",
|
|
"VllmModelForTextGeneration",
|
|
"is_text_generation_model",
|
|
"HasInnerState",
|
|
"has_inner_state",
|
|
"SupportsLoRA",
|
|
"supports_lora",
|
|
"SupportsMultiModal",
|
|
"supports_multimodal",
|
|
"SupportsPP",
|
|
"supports_pp",
|
|
] |