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
43 lines
730 B
Plaintext
43 lines
730 B
Plaintext
|
|
# mkdocs-material
|
|
# mkdocs-minify-plugin
|
|
# python-markdown-math
|
|
# regex
|
|
# ruff
|
|
|
|
# jinja2~=3.1
|
|
# markdown~=3.2
|
|
# mkdocs~=1.6
|
|
# mkdocs-material-extensions~=1.3
|
|
# pygments~=2.16
|
|
# pymdown-extensions~=10.2
|
|
|
|
# # Requirements for plugins
|
|
# babel~=2.10
|
|
# colorama~=0.4
|
|
# paginate~=0.5
|
|
# backrefs~=5.7.post1
|
|
# requests~=2.26
|
|
|
|
# Requirements for core
|
|
jinja2
|
|
markdown
|
|
mkdocs
|
|
mkdocs-material
|
|
mkdocs-material-extensions
|
|
pygments
|
|
pymdown-extensions
|
|
mkdocs-minify-plugin
|
|
python-markdown-math
|
|
|
|
mkdocs-git-revision-date-localized-plugin
|
|
# Requirements for plugins
|
|
babel
|
|
colorama
|
|
paginate
|
|
backrefs
|
|
requests
|
|
|
|
# Temporarily pin click until this is resolved in MkDocs, see
|
|
# https://github.com/mkdocs/mkdocs/issues/4014#issuecomment-3146508306
|
|
click |