Logo
Explore Help
Register Sign In
dylanyunlong/project_6
1
0
Fork 0
You've already forked project_6
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
ca6dcc81d2298d0cee5be66008bc2c07c965e556
project_6/upstream_ref/xllm/docs/zh/features/basics.md

10 lines
295 B
Markdown
Raw Normal View History

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 02:53:54 +00:00
# 基础知识
- xLLM使用一卡一进程模式,多卡之间使用rpc进行函数调用,模型计算过程中的数据通信使用device集合通信库。
- HCCL/LCCL是高性能集合通信,提供单机多卡以及多机多卡间的数据并行、模型并行集合通信方案。
Reference in New Issue Copy Permalink
Powered by Gitea Version: 1.24.3 Page: 46ms Template: 1ms
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API