f1f6370ed9
### What this PR does / why we need it?
This PR integrate suffix decoding (https://arxiv.org/abs/2411.04975)
from vllm (https://github.com/vllm-project/vllm/pull/25784)
#
Suffix Decoding is a dynamic n-gram matching method that:
1. Uses suffix trees to generate speculative tokens quickly using branch
frequency counts.
2. Can keep a history of prior model responses, which tends to work very
well with repetitive agentic use cases.
3. Can be dynamically updated with newly generated tokens, and FIFO
eviction of older requests.
#
### Does this PR introduce _any_ user-facing change?
This feature should be implemented as opt-in and remain seamless for
users who do not require suffix speculative decoding.
For users who wish to enable it, they must first install
arctic-inference:
`pip install arctic-inference
`
After installation, the suffix speculative decoding feature can be
enabled using the following speculative config:
`--speculative_config '{"method": "suffix", "num_speculative_tokens":
5}'
`
### How was this patch tested?
This PR is currently being tested on vLLM
main:83f478bb19
with PR https://github.com/vllm-project/vllm/pull/25784
In our previous testing, suffix decoding achieved a 13%-30% throughput
improvement over n-gram on the sonnet dataset, tested on vllm-ascend
v0.9.1 with concurrency ranging from 2 to 40.
- vLLM version: v0.11.2
---------
Signed-off-by: fluctlux <38945811+fluctlux@users.noreply.github.com>
55 lines
1.8 KiB
Python
55 lines
1.8 KiB
Python
import enum
|
|
from typing import Optional
|
|
|
|
import numpy as np
|
|
import torch
|
|
from vllm.config import CUDAGraphMode, VllmConfig
|
|
from vllm.v1.core.sched.output import SchedulerOutput
|
|
from vllm.v1.sample.metadata import SamplingMetadata
|
|
from vllm.v1.spec_decode.metadata import SpecDecodeMetadata
|
|
|
|
|
|
class SpecDcodeType(enum.Enum):
|
|
NGRAM = 0
|
|
EAGLE = 1
|
|
EAGLE3 = 2
|
|
MTP = 4
|
|
SUFFIX = 5
|
|
|
|
|
|
class Proposer:
|
|
|
|
def __init__(self,
|
|
vllm_config: VllmConfig,
|
|
device: torch.device = None,
|
|
runner=None):
|
|
pass
|
|
|
|
def load_model(self, model):
|
|
"""Called by load_model in model_runner"""
|
|
raise NotImplementedError
|
|
|
|
@torch.inference_mode()
|
|
def dummy_run(self,
|
|
num_tokens: int,
|
|
with_prefill: bool = False,
|
|
skip_attn: bool = False,
|
|
num_reqs: int = 0,
|
|
num_tokens_across_dp: Optional[torch.Tensor] = None,
|
|
aclgraph_runtime_mode: CUDAGraphMode = CUDAGraphMode.NONE,
|
|
batch_descriptor=None):
|
|
"""Called by dummy_run in modle_runner"""
|
|
raise NotImplementedError
|
|
|
|
def generate_token_ids(self,
|
|
valid_sampled_token_ids: list[np.ndarray],
|
|
sampling_metadata: SamplingMetadata = None,
|
|
scheduler_output: SchedulerOutput = None,
|
|
spec_decode_metadata: SpecDecodeMetadata = None,
|
|
positions: torch.Tensor = None,
|
|
num_scheduled_tokens: int = 0,
|
|
hidden_states: torch.Tensor = None,
|
|
attn_metadata=None,
|
|
aux_hidden_states: torch.Tensor = None):
|
|
"""Called by execute_model in model_runner"""
|
|
raise NotImplementedError |