[Feature] Sglang Tracing: Fine-Grained Tracking for Request Latency - Part 2 (#10804)
Signed-off-by: Feng Su <sufeng@linux.alibaba.com>
This commit is contained in:
@@ -95,6 +95,8 @@ SGLang supports various environment variables that can be used to configure its
|
||||
| --- | --- | --- |
|
||||
| `SGLANG_TORCH_PROFILER_DIR` | Directory for PyTorch profiler output | `/tmp` |
|
||||
| `SGLANG_PROFILE_WITH_STACK` | Set `with_stack` option (bool) for PyTorch profiler (capture stack trace) | `true` |
|
||||
| `SGLANG_OTLP_EXPORTER_SCHEDULE_DELAY_MILLIS` | Config BatchSpanProcessor.schedule_delay_millis if tracing is enabled | `500` |
|
||||
| `SGLANG_OTLP_EXPORTER_MAX_EXPORT_BATCH_SIZE` | Config BatchSpanProcessor.max_export_batch_size if tracing is enabled | `64` |
|
||||
|
||||
## Storage & Caching
|
||||
|
||||
|
||||
Reference in New Issue
Block a user