biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[gpt-oss] Enable gpt-oss on ampere (#22714)

Browse Source 
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
This commit is contained in:
Yongye Zhu
2025-08-12 06:21:44 -04:00
committed by GitHub
parent b8a9d0e429
commit 007dd90859
10 changed files with 26 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_platform.py
View File

@@ -25,5 +25,6 @@ class DummyPlatform(Platform):
compilation_config.custom_ops = ["all"]
def get_attn_backend_cls(self, backend_name, head_size, dtype,
kv_cache_dtype, block_size, use_v1, use_mla):
return "vllm_add_dummy_platform.dummy_attention_backend.DummyAttentionBackend" # noqa E501
kv_cache_dtype, block_size, use_v1, use_mla,
has_sink):
return "vllm_add_dummy_platform.dummy_attention_backend.DummyAttentionBackend" # noqa E501