Skip to content

GitLab

Unverified Commit e1684a76 authored by Thomas Parnell's avatar Thomas Parnell Committed by GitHub
Browse files

[Bugfix] Fix hard-coded value of x in context_attention_fwd (#6373) 


Signed-off-by: default avatarThomas Parnell <tpa@zurich.ibm.com>
parent a27f87da
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
vllm/attention/ops/prefix_prefill.py
View file @ e1684a76
...@@ -718,7 +718,7 @@ if triton.__version__ >= "2.1.0": ...@@ -718,7 +718,7 @@ if triton.__version__ >= "2.1.0":
b_ctx_len, b_ctx_len,
alibi_slopes, alibi_slopes,
v_cache.shape[3], v_cache.shape[3],
8, k_cache.shape[4],
o, o,
b_loc.stride(0), b_loc.stride(0),
b_loc.stride(1), b_loc.stride(1),
...@@ -768,7 +768,7 @@ if triton.__version__ >= "2.1.0": ...@@ -768,7 +768,7 @@ if triton.__version__ >= "2.1.0":
b_seq_len, b_seq_len,
b_ctx_len, b_ctx_len,
v_cache.shape[3], v_cache.shape[3],
8, k_cache.shape[4],
o, o,
b_loc.stride(0), b_loc.stride(0),
b_loc.stride(1), b_loc.stride(1),
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment