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

[Attention] MLA decode optimizations (#12528)

Browse Source 
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: simon-mo <simon.mo@hey.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
This commit is contained in:
Lucas Wilkinson
2025-01-31 02:49:37 -05:00
committed by GitHub
parent a1fc18c030
commit cabaf4eff3
31 changed files with 2266 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_platform.py
View File

@@ -5,5 +5,5 @@ class DummyPlatform(CudaPlatform):
device_name = "DummyDevice"
def get_attn_backend_cls(self, backend_name, head_size, dtype,
kv_cache_dtype, block_size, use_v1):
kv_cache_dtype, block_size, use_v1, use_mla):
return "vllm_add_dummy_platform.dummy_attention_backend.DummyAttentionBackend" # noqa E501