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.
37 lines
1.1 KiB
Python
37 lines
1.1 KiB
Python
"""vLLM: a high-throughput and memory-efficient inference engine for LLMs"""
|
|
|
|
from vllm.engine.arg_utils import AsyncEngineArgs, EngineArgs
|
|
from vllm.engine.async_llm_engine import AsyncLLMEngine
|
|
from vllm.engine.llm_engine import LLMEngine
|
|
from vllm.entrypoints.llm import LLM
|
|
from vllm.executor.ray_utils import initialize_ray_cluster
|
|
from vllm.inputs import PromptType, TextPrompt, TokensPrompt
|
|
from vllm.model_executor.models import ModelRegistry
|
|
from vllm.outputs import (CompletionOutput, EmbeddingOutput,
|
|
EmbeddingRequestOutput, RequestOutput)
|
|
from vllm.pooling_params import PoolingParams
|
|
from vllm.sampling_params import SamplingParams
|
|
|
|
from .version import __version__, __version_tuple__
|
|
|
|
__all__ = [
|
|
"__version__",
|
|
"__version_tuple__",
|
|
"LLM",
|
|
"ModelRegistry",
|
|
"PromptType",
|
|
"TextPrompt",
|
|
"TokensPrompt",
|
|
"SamplingParams",
|
|
"RequestOutput",
|
|
"CompletionOutput",
|
|
"EmbeddingOutput",
|
|
"EmbeddingRequestOutput",
|
|
"LLMEngine",
|
|
"EngineArgs",
|
|
"AsyncLLMEngine",
|
|
"AsyncEngineArgs",
|
|
"initialize_ray_cluster",
|
|
"PoolingParams",
|
|
]
|