earayu
commited on
Commit
·
51c6017
1
Parent(s):
c93625c
feat: add doc
Browse files
docs/LightRAG_concurrent_explain.md
CHANGED
|
@@ -239,11 +239,6 @@ Total:
|
|
| 239 |
- 4 chunks waiting for LLM response
|
| 240 |
```
|
| 241 |
|
| 242 |
-
### Scenario 3: Resource Bottleneck Analysis
|
| 243 |
-
|
| 244 |
-
**Timeline Example (max_parallel_insert=2, llm_model_max_async=4)**:
|
| 245 |
-
|
| 246 |
-
|
| 247 |
## 7. Performance Optimization Recommendations
|
| 248 |
|
| 249 |
### Understanding the Bottleneck
|
|
|
|
| 239 |
- 4 chunks waiting for LLM response
|
| 240 |
```
|
| 241 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 242 |
## 7. Performance Optimization Recommendations
|
| 243 |
|
| 244 |
### Understanding the Bottleneck
|
docs/assets/lightrag_llm_request_timeline.png
DELETED
Git LFS Details
|
docs/zh/LightRAG_concurrent_explain_zh.md
CHANGED
|
@@ -235,9 +235,6 @@ async def _process_single_content(chunk_key_dp: tuple[str, TextChunkSchema]):
|
|
| 235 |
- 4个chunks等待LLM响应
|
| 236 |
```
|
| 237 |
|
| 238 |
-
### 场景3：资源瓶颈分析
|
| 239 |
-
|
| 240 |
-
|
| 241 |
## 7. 性能优化建议
|
| 242 |
|
| 243 |
### 理解瓶颈
|
|
|
|
| 235 |
- 4个chunks等待LLM响应
|
| 236 |
```
|
| 237 |
|
|
|
|
|
|
|
|
|
|
| 238 |
## 7. 性能优化建议
|
| 239 |
|
| 240 |
### 理解瓶颈
|