002f9879b2
Replaces cherry-picked upstream_ref with complete source trees. xllm/ — Iluvatar official C++ inference engine (15MB, 1470 files) Complete: kernels → layers → models → runtime → scheduler → api Excluded: .git, binary images, third_party submodule checkouts ds_vllm/ — Iluvatar official vllm fork (8MB, 703 files) Included: csrc/ (ALL CUDA kernels), fused_moe/, qwen3_5 model, _custom_ops Excluded: tests, benchmarks, docs, examples (not needed for reference) Critical call chains now fully traceable: MoE: moe_topk_softmax_kernels.cuh → ixformer.h → fused_moe.cpp → layer GDN: qwen3_gated_delta_net_base.cpp → qwen3_5_gated_delta_net.cpp Attention: ixformer.h → xllm_paged_attention → attention.cpp
511 B
511 B
Continuous调度器
功能介绍
xLLM实现了支持continuous batching的调度策略，continuous_batch是一种动态批处理策略，它不等待批次填满，而是在有请求时就开始处理，同时持续接收新请求并将其加入正在执行的批次中，从而在保持高吞吐量的同时显著降低延迟。
使用方式
xLLM提供了continuous batching调度策略。目前enable_chunked_prefill默认值为true，开箱即用时默认调度器是chunked prefill调度器。