fix(BACKEND-ROCM): bind resource operations to the requested device
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 5/5
- 预计耗时
- 一周以上
- 新手友好度
- 35/100
- Issue 类型
- 缺陷
- 描述清晰度
- 基本清楚
- 活跃度
- 活跃
- 技术栈
- cpp
- 领域
- backend, testing-qa
调研方向
从 src/vt/rocm/rocm_backend.hip:220-284 开始，检查共享资源 API 以及针对 vt::Alloc(Device, ...) 缺失的 DeviceResourceOps 注册。在依赖原生 MoE 边界结果之前，先运行独立的 allocation-device 探针。完成要求一个涵盖指针和 stream 所有权、环境设备恢复、默认 stream 的复制和同步、主机线程、单设备行为以及图生命周期的双设备红色测试。
由索引模型根据 Issue 内容生成。
描述
Row: BACKEND-ROCM
ROCm resource methods use the ambient HIP device instead of their recorded device index. At base 6db4bef906859e864c82523c01107473f7dcca29, src/vt/rocm/rocm_backend.hip:220-284 calls hipMalloc, hipStreamCreate, hipMemsetAsync, hipMemcpyAsync, and hipStreamSynchronize without selecting device_ or the queue device. The backend registers no DeviceResourceOps override for vt::Alloc(Device, ...). The introducing source history is 50b0709b3.
A native MoE boundary test on two local gfx1100 devices exposed this assumption. Device-1-labeled buffers were constructed while device 0 remained current. The operator run returned 1 with three failed comparisons in the null-default-stream case. The other six cases passed. Untouched 0x5555 buffers and invalid reference values identify invalid test resource placement, not a valid native-kernel numerical result. An isolated allocation-device probe remains required before accepting the precise runtime diagnosis.
Owner: BACKEND-ROCM, resource and queue device ownership. The new MoE component test must explicitly allocate, copy, and build its reference on each intended device before testing native operation device selection. That scoped harness adaptation does not establish full-model execution on multiple GPUs.
Acceptance requires a committed spec, a red test through the shared resource API with a deliberately different ambient device, verified pointer and stream ownership, preserved ambient-device restoration, and correct default-stream copy and synchronization. Cover two devices, host threads, existing single-device behavior, and graph lifetimes. Run the pinned primary oracle for applicable resource behavior, fresh mutation review, and operator GPU gates. Keep native provider and resource ownership claims separate.
Local reproduction: /home/vikash/vllm.cpp-rdna3-moe-impl/build-rdna3-moe-hip/evidence/native-boundary-1.log and its operator receipt. Binary SHA256: 124546db69241940fd5ee88fb26cf71d6053a1dab7ad425915d0422dfc4854f2. The run held /home/vikash/gpu.lock, exposed local devices 0 and 1, and ran on 9 September 2026 UTC.
- 主要语言
- C++
- 星标
- 440
- 派生
- 55
- 平均合并
- 1 天 4 小时
- 30 天内合并 PR
- 366
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
mudler/vllm.cpp 的其他 Issue
-
难度 2/5 1-3 小时 新手友好度 84/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 82/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 70/100
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 88/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 84/100
维护者通常 1 天内回复
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 75/100
mpfaffenberger/privateer_reimagined#658 ·
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 85/100
microsoft/onnxruntime#33018 ·
维护者通常 2 天内回复
-
难度 2/5 1-3 小时 新手友好度 82/100
AXERA-TECH/ax-llm#81 ·
-
enhancement
难度 2/5 半天 新手友好度 78/100
ros-industrial/ros2_canopen#448 ·
-
难度 1/5 1 小时以内 新手友好度 78/100
维护者通常 1 天内回复