A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 21:00 UTC
Add authors to license header. (#14371)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com> Co-authored-by: Burkhard Ringlein <ngl@zurich.ibm.com> Co-authored-by: Jan van Lunteren <jvl@zurich.ibm.com>
Thomas Parnell committed
Mar 6, 2025 at 17:43 UTC
e642ec962cf2283f9aa44492727e6efc17a32129
1 file changed
+5
vllm/attention/ops/chunked_prefill_paged_decode.py
+5
@@ -1,5 +1,10 @@
1
# SPDX-License-Identifier: Apache-2.0
2
3
+# Authors:
4
+# - Burkhard Ringlein
5
+# - Jan van Lunteren
6
+# - Thomas Parnell
7
+
8
import torch
9
import triton
10
import triton.language as tl