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

[ROCM][KERNEL] Paged attention for V1 (#15720)

Browse Source 
Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Signed-off-by: root <root@banff-cyxtera-s65-4.amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: root <root@banff-cyxtera-s65-4.amd.com>
This commit is contained in:
Aleksandr Malyshev
2025-04-02 19:48:00 -07:00
committed by GitHub
parent bd7599d34a
commit e73ff24e31
11 changed files with 219 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/kernels/test_prefix_prefill.py
View File

@@ -164,6 +164,7 @@ def test_contexted_kv_attention(
block_table,
b_start_loc,
b_seq_len,
MAX_CTX_LEN,
max_input_len,
k_scale,
v_scale,
@@ -180,6 +181,7 @@ def test_contexted_kv_attention(
block_table,
b_start_loc,
b_seq_len,
MAX_CTX_LEN,
max_input_len,
k_scale,
v_scale,
@@ -397,6 +399,7 @@ def test_contexted_kv_attention_alibi(
block_table,
b_start_loc,
b_seq_len,
MAX_CTX_LEN,
max_input_len,
k_scale,
v_scale,
@@ -413,6 +416,7 @@ def test_contexted_kv_attention_alibi(
block_table,
b_start_loc,
b_seq_len,
MAX_CTX_LEN,
max_input_len,
k_scale,
v_scale,