e2237819a9
### What this PR does / why we need it?
The incorrect regular expression syntax `.*[UE4M3|ue4m3].*` actually
ignores all words containing any of the following characters: `u, e, 4,
m, 3, |`
```yaml
extend-ignore-identifiers-re = [".*Unc.*", ".*_thw",
".*UE8M0.*", ".*[UE4M3|ue4m3].*", ".*eles.*", ".*fo.*", ".*ba.*",
".*ot.*", ".*[Tt]h[rR].*"]
```
===fix===>
```yaml
extend-ignore-identifiers-re = [".*Unc.*", ".*_thw",
".*UE8M0.*", ".*(UE4M3|ue4m3]).*", ".*eles.*", ".*fo.*", ".*ba.*",
".*ot.*", ".*[Tt]h[rR].*"]
```
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.15.0
- vLLM main:
9562912cea
Signed-off-by: MrZ20 <2609716663@qq.com>
54 lines
1.5 KiB
Python
54 lines
1.5 KiB
Python
import enum
|
|
|
|
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
|
|
MEDUSA = 6
|
|
|
|
|
|
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,
|
|
in_graph_capturing: bool = False,
|
|
num_reqs: int = 0,
|
|
num_tokens_across_dp: torch.Tensor | None = None,
|
|
aclgraph_runtime_mode: CUDAGraphMode = CUDAGraphMode.NONE,
|
|
batch_descriptor=None,
|
|
):
|
|
"""Called by dummy_run in model_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,
|
|
aux_hidden_states: torch.Tensor = None,
|
|
):
|
|
"""Called by execute_model in model_runner"""
|
|
raise NotImplementedError
|