chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[NVIDIA] Add flashinfer all-to-all MOE dispatcher (#14668)

Browse Source
This commit is contained in:
Trevor Morris
2026-01-24 22:59:55 +08:00
committed by GitHub
parent 458a43d4ac
commit 2c2c4e446b
14 changed files with 723 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/advanced_features/expert_parallelism.md
+1
View File
@@ -15,6 +15,7 @@ SGLang's EP integrates diverse, highly efficient backends for different use case
| **`none` (default)** | Disables all-to-all for EP. Uses All-Reduce or All-Gather for token dispatch. | Hybrid EP and TP setups. |
| `deepep` | DeepEP, a communication library for efficient token shuffling in MoE models. | Large-scale EP deployments. |
| `mooncake` | An extension of DeepEP for elastic inference, leveraging RDMA for high-performance data transfers. | Elastic EP serving. |
| `flashinfer` | Flashinfer implementation of all-to-all. | Large-scale EP deployments. |
| `ascend_fuseep` | Ascend NPU native fused all-to-all communication. | Ascend NPU deployments. |
DeepEP and Mooncake backends support two modes for token dispatch: `normal` mode (optimized for prefill workloads with high throughput) and `low_latency` mode (optimized for decode workloads with low latency and CUDA Graph compatibility). Users are recommended to set `--deepep-mode auto` to enable automatic dispatch mode switching during runtime. Setting `--deepep-mode normal` or `--deepep-mode low_latency` is useful for debugging or development purposes.
docs/references/environment_variables.md
+1
View File
@@ -62,6 +62,7 @@ SGLang supports various environment variables that can be used to configure its
| --- | --- | --- |
| `SGLANG_DEEPEP_BF16_DISPATCH` | Use Bfloat16 for dispatch | `"false"` |
| `SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK` | The maximum number of dispatched tokens on each GPU | `"128"` |
| `SGLANG_FLASHINFER_NUM_MAX_DISPATCH_TOKENS_PER_RANK` | The maximum number of dispatched tokens on each GPU for --moe-a2a-backend=flashinfer | `"1024"` |
| `SGLANG_DEEPEP_LL_COMBINE_SEND_NUM_SMS` | Number of SMs used for DeepEP combine when single batch overlap is enabled | `"32"` |
| `SGLANG_BLACKWELL_OVERLAP_SHARED_EXPERTS_OUTSIDE_SBO` | Run shared experts on an alternate stream when single batch overlap is enabled on GB200. When not setting this flag, shared experts and down gemm will be overlapped with DeepEP combine together. | `"false"` |