7f2673ea2d
1. fix https://github.com/vllm-project/vllm/pull/28542 The model structure modifications we involved in are: - Qwen2.5-VL(still exist some patch) - Qwen2-VL - Qwen2 - DeepSeek series - Qwen-moe series 2. fix https://github.com/vllm-project/vllm/pull/29121 the output token now type changed from np to `list[list[int]]` 3. fix https://github.com/vllm-project/vllm/pull/29262 `xformers` backend for multimodal now has been deprecated 4. fix https://github.com/vllm-project/vllm/pull/29342 5. fix https://github.com/vllm-project/vllm/pull/28579 6. fix https://github.com/vllm-project/vllm/pull/28718 7. fix https://github.com/vllm-project/vllm/issues/28665 8. fix https://github.com/vllm-project/vllm/pull/26847 vllm introduced the `optimization-level`, some default config has been changed, and the param `--enforce-eager` has been deprecated 9. fix http://github.com/vllm-project/vllm/pull/29223 it retuns tuple for sampler. 10. fix https://github.com/vllm-project/vllm/pull/29471 we'll remove the related patch to avoid this kind of error. Co-authored-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: wangli <wangli858794774@gmail.com> - vLLM version: v0.11.2 --------- Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: wangli <wangli858794774@gmail.com> Signed-off-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: wangli <wangli858794774@gmail.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com>
54 lines
1.8 KiB
Python
54 lines
1.8 KiB
Python
import enum
|
|
from typing import Optional
|
|
|
|
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[list[int]],
|
|
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 |