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

[Attention Backend] Extend hpc_ops dynamic-scheduled decode to bf16 (#32304)

Browse Source 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Halcyon <56064364+VAthree@users.noreply.github.com>
This commit is contained in:
Xiaoyu Zhang
2026-07-27 21:31:04 +08:00
committed by GitHub
co-authored by Claude Fable 5 Halcyon
parent 5656de2d9a
commit 8d6549bc40
7 changed files with 73 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/docs/advanced_features/attention_backend.mdx
+1 -1
View File
@@ -627,7 +627,7 @@ python3 -m sglang.launch_server \
--trust-remote-code
```
- HPC-Ops (MHA kernels from [HPC-Ops](https://github.com/Tencent/hpc-ops) by the Tencent Hunyuan AI Infra team; Hopper+, requires installing the `hpc` package from source, page size 64, bf16 or fp8_e4m3 KV cache, head_dim 128, q/kv head group 4 or 8)
- HPC-Ops (MHA kernels from [HPC-Ops](https://github.com/Tencent/hpc-ops) by the Tencent Hunyuan AI Infra team; Hopper (SM90) only, requires installing the `hpc` package from source, page size 64, bf16 or fp8_e4m3 KV cache, head_dim 128, q/kv head group 4 or 8)
```bash Command
python3 -m sglang.launch_server \
--model Qwen/Qwen3-30B-A3B-Instruct-2507-FP8 \