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
main
project_6/ixformer_sdk/contrib/flashinfer/sampling.py

15 lines
164 B
Python
Raw Permalink Normal View History

feat(CRITICAL): 从 GitHub 扫描搬运 ixformer SDK + xllm 完整 GDN/MoE 代码 来源: 1. Chranos/ixformer (GitHub) → ixformer_sdk/ (230 files, 70K lines) - inference/functions/vllm.py: vllm_moe_topk_softmax 完整实现 (2033 lines) - inference/functions/moe.py: MoE ops 完整实现 (1380 lines) - contrib/vllm_flash_attn/: FA2 Python 接口 (1018 lines) - contrib/tgi/fused_moe.py: TGI fused MoE (429 lines) - csrc/include/ixformer/: C++ kernel headers + cmake 2. Deep-Spark/xllm (GitHub) → upstream_ref/xllm_latest/ (+15 files) - npu_torch/qwen3_5_decoder_layer_impl.cpp/.h - npu_torch/qwen3_5_gated_delta_net.cpp/.h - npu_torch/qwen3_next_*.cpp/.h (6 files) - npu_torch/attention.cpp/.h + fused_moe.cpp/.h + CMakeLists.txt - models/llm/qwen3_5.h + qwen3_5_mtp.h + qwen3_next.h - models/vlm/qwen3_5.h 调用链完整性: ixformer_sdk/inference/functions/vllm.py → ops.infer.moe_topk_softmax() (C++ 层) → 这就是 base 镜像 libixformer.so 里的实现 upstream_ref/xllm_latest/core/layers/ilu/fused_moe.cpp → ixformer::infer::topk_softmax() (直接 C++ 调用) → ixformer::infer::group_gemm() → 完整 7-step MoE pipeline
2026-08-11 02:31:56 +00:00
def min_p_sampling_from_probs():
pass
def top_k_renorm_prob():
pass
def top_k_top_p_sampling_from_probs():
pass
def top_p_renorm_prob():
pass
Reference in New Issue Copy Permalink
Powered by Gitea Version: 1.24.3 Page: 99ms Template: 2ms
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