Commit Graph
10 Commits
Author SHA1 Message Date
Lucas Wilkinson 1dc8a70b6d [Attention] Support multiple attention metadata builders per kv_cache_spec + proper local attention no hybrid kv cache fix (#21588)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-08-06 18:40:52 -07:00
Thomas Parnell 4abfd8796f [V1] [Hybrid] Validate compatibility of attention backend batch reordering at init time (#21557)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
2025-08-02 05:29:40 -07:00
Maximilien de BayserandRussell Bryant 1cd6eaba54 Support encoder-only models without KV-Cache (#21270)
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
2025-07-26 21:09:52 +08:00
Li, Jiang e3a0e43d7f [bugfix] Fix auto thread-binding when world_size > 1 in CPU backend and refactor code (#21032)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2025-07-19 05:13:55 -07:00
Rui Qiao 217937221b Elastic Expert Parallel Initial Support (#20775)
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
2025-07-18 17:46:09 -07:00
Cyrus Leung 45badd05d0 [Core] Set pooling params based on task and model (#21128)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-07-18 05:41:17 -07:00
Jee Jee Li 1caca5a589 [Misc] Add SPDX-FileCopyrightText (#20428)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-07-04 07:40:42 +00:00
Li, Jiang 53da4cd397 [Bugfix][CPU] Fix InputBatch for pooling models in the CPU v1 (#20014)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2025-06-24 13:20:04 +00:00
Li, Jiang 6458721108 [CPU] Refine default config for the CPU backend (#19539)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2025-06-13 13:27:39 +08:00
Li, Jiang 4555143ea7 [CPU] V1 support for the CPU backend (#16441) 2025-06-03 18:43:01 -07:00