[Rust Server] Add e2e latency metadata and fix Sarashina import (#35125)

This commit is contained in:
Lianmin Zheng
2026-08-18 02:08:07 -07:00
committed by GitHub
parent 880ab72f34
commit 70ee6b1714
2 changed files with 253 additions and 29 deletions
@@ -24,11 +24,10 @@ from sglang.srt.layers.logits_processor import LogitsProcessor
from sglang.srt.layers.pooler import Pooler, PoolingType
from sglang.srt.layers.quantization.base_config import QuantizationConfig
from sglang.srt.managers.mm_utils import (
MultimodalDataItem,
MultimodalInputs,
MultiModalityDataPaddingPatternMultimodalTokens,
general_mm_embed_routine,
)
from sglang.srt.managers.schedule_batch import MultimodalDataItem, MultimodalInputs
from sglang.srt.model_executor.forward_batch_info import ForwardBatch
from sglang.srt.model_loader.weight_utils import default_weight_loader
from sglang.srt.models.llama import LlamaForCausalLM