zijie-tian/nano-vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

🔧 chore: add Claude rules for agent result format and multi-GPU debugging

Browse Source 
- Add agent-result-format.md: standardize output formats for background agents
- Add multi-gpu-debugging.md: guidelines for parallel GPU testing workflows
- Update CLAUDE.md: add documentation index entry for chunked offload issue

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Zijie Tian
2026-01-20 23:41:08 +08:00
parent 6180055ed8
commit 512e1e5401
3 changed files with 667 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
CLAUDE.md
View File

@@ -23,6 +23,15 @@ Nano-vLLM is a lightweight vLLM implementation (~1,200 lines) for fast offline L
| [`docs/ruler_32k_chunked_offload_issue.md`](docs/ruler_32k_chunked_offload_issue.md) | ⚠️ OPEN ISSUE: 32K chunked offload accuracy problem (20% error rate in RULER) |
| [`docs/chunked_attention_solutions.md`](docs/chunked_attention_solutions.md) | 🔧 SOLUTIONS: Chunked attention 准确性问题的代码分析和解决方案 |
## Rules Index
| Rule | Purpose |
|------|---------|
| [`.claude/rules/multi-gpu-debugging.md`](.claude/rules/multi-gpu-debugging.md) | **Multi-GPU debugging**: GPU allocation (1-2 for validation, rest for exploration), single-task validation policy |
| [`.claude/rules/gpu-testing.md`](.claude/rules/gpu-testing.md) | GPU type detection, card assignment, needle test requirements |
| [`.claude/rules/sparse-policy.md`](.claude/rules/sparse-policy.md) | SparsePolicy implementation requirements |
| [`.claude/rules/planning-with-files.md`](.claude/rules/planning-with-files.md) | Planning file management for complex tasks |
## GPU Mutex for Multi-Instance Debugging
**IMPORTANT**: When running multiple Claude instances for parallel debugging, different rules apply based on script type: