biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Deprecation][2/N] Replace --task with --runner and --convert (#21470)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Cyrus Leung
2025-07-28 10:42:40 +08:00
committed by GitHub
parent 8f605ee309
commit 86ae693f20
94 changed files with 1117 additions and 1083 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
vllm/transformers_utils/tokenizer_group.py
View File

@@ -3,6 +3,8 @@
from typing import Optional
from typing_extensions import assert_never
from vllm.config import LoRAConfig, ModelConfig, SchedulerConfig
from vllm.lora.request import LoRARequest
from vllm.transformers_utils.tokenizer import (AnyTokenizer, encode_tokens,
@@ -108,6 +110,14 @@ class TokenizerGroup:
def init_tokenizer_from_configs(model_config: ModelConfig,
scheduler_config: SchedulerConfig,
lora_config: Optional[LoRAConfig]):
runner_type = model_config.runner_type
if runner_type == "generate" or runner_type == "draft":
truncation_side = "left"
elif runner_type == "pooling":
truncation_side = "right"
else:
assert_never(runner_type)
return TokenizerGroup(
tokenizer_id=model_config.tokenizer,
enable_lora=bool(lora_config),
@@ -117,4 +127,4 @@ def init_tokenizer_from_configs(model_config: ModelConfig,
tokenizer_mode=model_config.tokenizer_mode,
trust_remote_code=model_config.trust_remote_code,
revision=model_config.tokenizer_revision,
truncation_side=model_config.truncation_side)
truncation_side=truncation_side)