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

Re-enable Flashinfer TRTLLM GEN MHA and Add Unit Test (#12885)

Browse Source
This commit is contained in:
Sam
2025-11-11 12:17:43 +08:00
committed by GitHub
parent 9caca6a45c
commit 3594815a8b
3 changed files with 65 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
python/sglang/srt/layers/attention/attention_registry.py
View File

@@ -199,7 +199,8 @@ def attn_backend_wrapper(runner: "ModelRunner", full_attn_backend: "AttentionBac
if is_blackwell():
assert (
runner.server_args.attention_backend == "triton"
), "triton backend is the only supported backend on Blackwell GPUs for hybrid GDN models, use --attention-backend triton to specify the backend."
or runner.server_args.attention_backend == "trtllm_mha"
), "triton or trtllm_mha backend are the only supported backends on Blackwell GPUs for hybrid GDN models, use --attention-backend triton or --attention-backend trtllm_mha to specify the backend."
if is_npu():
assert (
runner.server_args.attention_backend == "ascend"