dylanyunlong/project_6
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
900ae0b1efc19e46cd313eb3ba7eb694fa596f6b
project_6/upstream_ref/xllm/docs/en/features/basics.md
EX Engine 002f9879b2 ref(upstream): FULL TREE — Deep-Spark xllm (1470) + ds_vllm csrc/models (703) 
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
2026-08-10 02:54:03 +00:00

428 B
Raw Blame History

Basics

  • xLLM uses a one-device-per-process architecture. Across multiple devices, RPC is used for function calls, and data communication during model computation uses device collective communication libraries.

  • HCCL/LCCL are high-performance collective communication frameworks that provide data-parallel and model-parallel collective communication for both single-node multi-device and multi-node multi-device scenarios.