dylanyunlong/project_6
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

upstream(xllm): sync to jd-opensource/xllm latest + revert serving_chat.py

Browse Source 
搬运 jd-opensource/xllm 最新代码到 upstream_ref/xllm_latest/:
- core/kernels/ilu/ 10 files (ixformer.h API 不变)
- core/layers/ilu/ 4 files (fused_moe.cpp config 访问从 FLAGS→singleton)
- core/layers/npu_torch/ 14 files (qwen3_gated_delta_net_base.cpp 576→1164行,
  新增 repeat_tensor_heads, checkpoint_stride, spec_verify 等 GDN 功能)
- models/llm/ 5 files (qwen3_5.h 模型注册重构, 新增 qwen3_5_mtp_base.h)
- models/vlm/ 1 file (qwen3_5.h 218→440行)

serving_chat.py: 还原到 8030a11b 原版,删掉 6dcf3590 的语法错误 min(8192,
(缺右括号导致 py_compile 失败)
This commit is contained in:
project6-dev
2026-08-12 04:22:34 +00:00
parent 6dcf3590d5
commit d025b08a95
35 changed files with 1595 additions and 593 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
upstream_ref/xllm_latest/models/llm/qwen3_next.h
View File

@@ -1,4 +1,4 @@
/* Copyright 2026 The xLLM Authors. All Rights Reserved.
/* Copyright 2025-2026 The xLLM Authors.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.