[EPLB] Make async EPLB default (#43219)

Signed-off-by: Markov Ilya <markovilya19@gmail.com>
Co-authored-by: Markov Ilya <markovilya19@gmail.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Ilya Markov
2026-05-29 18:07:16 +00:00
committed by GitHub
co-authored by Markov Ilya Tyler Michael Smith
parent 84b2a8a7e7
commit 4aaba00f92
7 changed files with 15 additions and 15 deletions
+1 -1
View File
@@ -151,7 +151,7 @@ Configure EPLB with the `--eplb-config` argument, which accepts a JSON string. T
| `step_interval` | Frequency of rebalancing (every N engine steps) | 3000 |
| `log_balancedness` | Log balancedness metrics (avg tokens per expert ÷ max tokens per expert) | `false` |
| `num_redundant_experts` | Additional global experts per EP rank beyond equal distribution | `0` |
| `use_async` | Use non-blocking EPLB for reduced latency overhead | `false` |
| `use_async` | Use non-blocking EPLB for reduced latency overhead | `true` |
| `policy` | The policy type for expert parallel load balancing | `"default"` |
| `communicator` | Backend for expert weight transfers: `"torch_nccl"`, `"torch_gloo"`, `"pynccl"`, `"nixl"`, or `null` (auto) | `null` |