chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[FlashInfer v0.6.4] [RL] Integrate FlashInfer mxfp8 gemm, MoE, and routed MoE (#19537)

Browse Source
This commit is contained in:
Ziang Li
2026-03-10 15:37:57 -07:00
committed by GitHub
parent bd460e9565
commit 76ee4bb98c
14 changed files with 671 additions and 86 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/advanced_features/server_arguments.md
View File

@@ -312,7 +312,7 @@ Please consult the documentation below and [server_args.py](https://github.com/s
| --- | --- | --- | --- |
| `--expert-parallel-size`<br>`--ep-size`<br>`--ep` | The expert parallelism size. | `1` | Type: int |
| `--moe-a2a-backend` | Select the backend for all-to-all communication for expert parallelism. | `none` | `none`, `deepep`, `mooncake`, `mori`, `ascend_fuseep`|
| `--moe-runner-backend` | Choose the runner backend for MoE. | `auto` | `auto`, `deep_gemm`, `triton`, `triton_kernel`, `flashinfer_trtllm`, `flashinfer_cutlass`, `flashinfer_mxfp4`, `flashinfer_cutedsl`, `cutlass` |
| `--moe-runner-backend` | Choose the runner backend for MoE. | `auto` | `auto`, `deep_gemm`, `triton`, `triton_kernel`, `flashinfer_trtllm`, `flashinfer_trtllm_routed`, `flashinfer_cutlass`, `flashinfer_mxfp4`, `flashinfer_cutedsl`, `cutlass` |
| `--flashinfer-mxfp4-moe-precision` | Choose the computation precision of flashinfer mxfp4 moe | `default` | `default`, `bf16` |
| `--enable-flashinfer-allreduce-fusion` | Enable FlashInfer allreduce fusion with Residual RMSNorm. | `False` | bool flag (set to enable) |
| `--enable-aiter-allreduce-fusion` | Enable aiter allreduce fusion with Residual RMSNorm. | `False` | bool flag (set to enable) |