biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[MoE Refactor] Rename "naive" all2all backend (#36294)

Browse Source 
Signed-off-by: Bill Nell <bnell@redhat.com>
This commit is contained in:
bnellnm
2026-03-19 15:50:34 -04:00
committed by GitHub
parent 4ee847e400
commit 91be5f9be3
6 changed files with 15 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/serving/expert_parallel_deployment.md
View File

@@ -23,7 +23,6 @@ vLLM provides multiple communication backends for EP. Use `--all2all-backend` to
| `deepep_low_latency` | Multi-node decode | CUDA graph support, masked layout, optimized for decode | Decode-dominated workloads, low-latency scenarios |
| `flashinfer_nvlink_one_sided` | MNNVL systems | FlashInfer's one-sided A2A strategy for multi-node NVLink | High-throughput workloads |
| `flashinfer_nvlink_two_sided` | MNNVL systems | FlashInfer's two-sided A2A strategy for multi-node NVLink | Systems with NVLink across nodes |
| `naive` | Testing/debugging | Simple broadcast-based implementation | Debugging, not recommended for production |
## Single Node Deployment