- 31 Aug, 2024 1 commit
-
-
Pavani Majety authored
-
- 30 Aug, 2024 2 commits
-
-
Woosuk Kwon authored
-
Richard Liu authored
-
- 29 Aug, 2024 2 commits
-
-
Pavani Majety authored
[Core][Kernels] Enable FP8 KV Cache with Flashinfer backend. + BugFix for kv_cache_dtype=auto (#7985) Co-authored-by:
Simon Mo <simon.mo@hey.com> Co-authored-by:
Cody Yu <hao.yu.cody@gmail.com>
-
youkaichao authored
-
- 28 Aug, 2024 1 commit
-
-
Pavani Majety authored
Co-authored-by:
-
- 27 Aug, 2024 1 commit
-
-
Cody Yu authored
-
- 21 Aug, 2024 1 commit
-
-
LI MOU authored
[BUG] fix crash on flashinfer backend with cudagraph disabled, when attention group_size not in [1,2,4,8] (#7509)
-
- 20 Aug, 2024 1 commit
-
-
Antoni Baum authored
-
- 16 Aug, 2024 2 commits
-
-
William Lin authored
Co-authored-by: -
youkaichao authored
-
- 12 Aug, 2024 3 commits
-
-
jon-chuang authored
Co-authored-by: -
Woosuk Kwon authored
-
Lily Liu authored
-
- 09 Aug, 2024 2 commits
-
-
Antoni Baum authored
-
Alexander Matveev authored
-
- 07 Aug, 2024 1 commit
-
-
Lily Liu authored
-
- 05 Aug, 2024 1 commit
-
-
Cody Yu authored
-
- 03 Aug, 2024 1 commit
-
-
Zach Zheng authored
-
- 02 Aug, 2024 1 commit
-
-
Lily Liu authored
-
- 01 Aug, 2024 1 commit
-
-
Woosuk Kwon authored
-
- 27 Jul, 2024 2 commits
-
-
Woosuk Kwon authored
-
Woosuk Kwon authored
-
- 25 Jul, 2024 1 commit
-
-
Cody Yu authored
-
- 24 Jul, 2024 2 commits
-
-
Antoni Baum authored
-
Antoni Baum authored
-
- 23 Jul, 2024 1 commit
-
-
Cody Yu authored
-
- 20 Jul, 2024 2 commits
-
-
Matt Wong authored
[Bugfix][CI/Build][Hardware][AMD] Fix AMD tests, add HF cache, update CK FA, add partially supported model notes (#6543)
-
Cyrus Leung authored
-
- 18 Jul, 2024 1 commit
-
-
Noam Gat authored
[Bugfix] Update flashinfer.py with PagedAttention forwards - Fixes Gemma2 OpenAI Server Crash (#6501)
-
- 17 Jul, 2024 1 commit
-
-
Cody Yu authored
-
- 16 Jul, 2024 1 commit
-
-
Michael Goin authored
-
- 12 Jul, 2024 1 commit
-
-
Woosuk Kwon 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>
-
- 04 Jul, 2024 2 commits
-
-
Lily Liu authored
Co-authored-by: -
Gregory Shtrasberg authored
[ROCm][AMD][Model]Adding alibi slopes support in ROCm triton flash attention and naive flash attention (#6043) Co-authored-by:Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
-
- 01 Jul, 2024 1 commit
-
-
Antoni Baum authored
-
- 28 Jun, 2024 3 commits
-
-
Lily Liu authored
Co-authored-by:LiuXiaoxuanPKU <llilyliupku@gmail.com>, bong-furiosa <bongwon.jang@furiosa.ai>
-
Ilya Lavrenov authored
-
Woosuk Kwon authored
-
