anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Perf][NPU] Enable native GQA & fused AddNorm for MiniMax-H3 encoder (#6040)

Browse Source 
Signed-off-by: MarkPoloChina <1228479724@qq.com>
Signed-off-by: XiongZhongwei <1228479724@qq.com>
This commit is contained in:
XiongZhongwei authored and GitHub committed 2026-08-26 09:14:05 +08:00
1 parent a708ae5b7a
commit 40dcfdbb43
11 files changed
+520 -28
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/config/test_config_import_cycle.py
+2
View File
@@ -66,6 +66,8 @@ def test_npu_platform_defers_minimax_h3_encoder_patch() -> None:
runtime_src = src[runtime_start:]
assert "apply_minimax_h3_qwen3vl_patch" not in init_src
assert "apply_minimax_h3_qwen3vl_patch" in runtime_src
assert "apply_minimax_h3_qwen3vl_sdpa_patch" not in init_src
assert "apply_minimax_h3_qwen3vl_sdpa_patch" in runtime_src
assert "apply_minimax_h3_qwen3vl_swiglu_patch" in runtime_src