- 23 Jan, 2025 1 commit
-
-
Gregory Shtrasberg authored
Signed-off-by:
Gregory Shtrasberg <Gregory.Shtrasberg@amd.com> Co-authored-by:
Micah Williamson <micah.williamson@amd.com>
-
- 22 Jan, 2025 1 commit
-
-
youkaichao authored
Signed-off-by:youkaichao <youkaichao@gmail.com>
-
- 22 Nov, 2024 1 commit
-
-
youkaichao authored
Signed-off-by:youkaichao <youkaichao@gmail.com>
-
- 04 Nov, 2024 1 commit
-
-
Yang Zheng authored
Co-authored-by:Yang Zheng(SW)(Alex) <you@example.com>
-
- 02 Nov, 2024 1 commit
-
-
sroy745 authored
-
- 01 Nov, 2024 1 commit
-
-
Peter Salas authored
Signed-off-by:Peter Salas <peter@fixie.ai>
-
- 31 Oct, 2024 1 commit
-
-
sasha0552 authored
[Bugfix] Fix `illegal memory access` error with chunked prefill, prefix caching, block manager v2 and xformers enabled together (#9532) Signed-off-by:sasha0552 <admin@sasha0552.org>
-
- 21 Oct, 2024 1 commit
-
-
Thomas Parnell authored
Signed-off-by:Thomas Parnell <tpa@zurich.ibm.com>
-
- 17 Oct, 2024 1 commit
-
-
Kuntai Du authored
Removing the block manager v1. This is the initial piece of prefix-caching-centric design. In order to achieve prefix-caching-centric design, we need to simplify the code path so that we only use v2 block manager (which has much higher performance on prefix caching).
-
- 12 Oct, 2024 1 commit
-
-
Lily Liu authored
-
- 01 Oct, 2024 1 commit
-
-
Lily Liu authored
-
- 18 Sep, 2024 1 commit
-
-
Aaron Pham authored
Signed-off-by:
Aaron Pham <contact@aarnphm.xyz> Co-authored-by:
Cyrus Leung <cyrus.tl.leung@gmail.com>
-
- 17 Sep, 2024 1 commit
-
-
sroy745 authored
-
- 20 Aug, 2024 1 commit
-
-
Antoni Baum authored
-
- 09 Aug, 2024 2 commits
-
-
Antoni Baum authored
-
Alexander Matveev authored
-
- 05 Aug, 2024 1 commit
-
-
Cody Yu authored
-
- 01 Aug, 2024 1 commit
-
-
Woosuk Kwon authored
-
- 25 Jul, 2024 1 commit
-
-
Cody Yu authored
-
- 23 Jul, 2024 1 commit
-
-
Cody Yu authored
-
- 20 Jul, 2024 1 commit
-
-
Cyrus Leung authored
-
- 17 Jul, 2024 1 commit
-
-
Cody Yu authored
-
- 08 Jul, 2024 1 commit
-
-
afeldman-nm authored
[Kernel] Correctly invoke prefill & decode kernels for cross-attention (towards eventual encoder/decoder model support) (#4888) Co-authored-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-