Commit Graph

503 Commits

Author SHA1 Message Date
Cyrus Leung
69244e67e6 [Core] Use key-only cache for BaseMultiModalProcessor (#23018)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-27 14:19:13 +08:00
Cyrus Leung
50fede6634 [V1] Enable V1 for compute capability < 8.0 + FP32 (#23614)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-26 03:00:18 -07:00
rongfu.leng
1b9b16649c [Misc] update dict parse to EPLBConfig from json dumps to dict unpacking (#23305)
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
2025-08-24 08:06:34 +00:00
Didier Durand
22cf679aad [Doc]: fix various typos in multiple files (#23179)
Signed-off-by: Didier Durand <durand.didier@gmail.com>
2025-08-22 10:38:46 -07:00
Matthew Bonanni
19fe1a0510 [Kernel] Add FP8 support with FlashMLA backend (#22668)
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
2025-08-22 02:26:32 +00:00
22quinn
480bdf5a7b [Core] Support custom executor qualname (#23314)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
2025-08-22 09:40:54 +08:00
Robert Shaw
c8e33c72c6 [V1] Remove unnecessary check for main thread (#23298)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
2025-08-21 14:08:35 +00:00
22quinn
f571ff8eb6 [Sampler] Support returning final logprobs (#22387)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-08-20 21:28:32 -07:00
Michael Goin
bbea1cefdd [CI Bugfix] Fix CI by fully removing --enable-prompt-adapter (#23284)
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-08-20 17:18:12 -07:00
rongfu.leng
4fbda0b20c [Feature] use --eplb_config to set eplb param (#20562)
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-08-20 14:07:28 -07:00
Cyrus Leung
5efd6905bc [CLI][Doc] Formalize --mm-encoder-tp-mode (#23190)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-20 23:42:28 +08:00
rongfu.leng
38217877aa [Fix] fix offline env use local mode path (#22526)
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
2025-08-20 13:34:49 +00:00
Nikhil Suryawanshi
78dba404ad [Hardware][IBM Z]Enable v1 for s390x and s390x dockerfile fixes (#22725)
Signed-off-by: Nikhil Suryawanshi <suryawanshin74@gmail.com>
2025-08-19 04:40:37 +00:00
afeldman-nm
bf7f470b22 [V1] Logits processors extensibility (#19912)
Signed-off-by: Andrew Feldman <afeldman@redhat.com>
Signed-off-by: Andrew Feldman <afeld2012@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Andrew Feldman <afeld2012@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-08-16 12:59:17 -07:00
Maximilien de Bayser
52ce1420e9 Fix handling of max_num_batched_tokens for pooling tasks (#23004)
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
2025-08-16 17:36:30 +00:00
Thomas Parnell
75531a6c13 [V1] [Hybrid] Support using float32 for state in Hybrid Models (Mamba2, Mamba1, Minimax) (#22928)
Signed-off-by: Daniel Afrimi <danielafrimi8@gmail.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Daniel Afrimi <danielafrimi8@gmail.com>
Co-authored-by: Burkhard Ringlein <ngl@zurich.ibm.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
2025-08-15 12:57:06 +00:00
Roger Wang
49252cf59e [MM] Allow skipping memory profiling for multimodal models. (#22950)
Signed-off-by: Roger Wang <hey@rogerw.me>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-08-15 11:41:38 +00:00
Cyrus Leung
dbe298046c [Bugfix] Fix parsing of --disable-mm-preprocessor-cache (#22909)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-14 08:09:44 -07:00
Woosuk Kwon
71683ca6f6 [V0 Deprecation] Remove multi-step scheduling (#22138)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
2025-08-12 20:18:39 -07:00
Harry Mellor
4fbd8bb597 Fix passing SpeculativeConfig from the CLI (#22652)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-08-11 22:13:32 -07:00
wang.yuqi
84cf78acee [Model] Pooling models default to using chunked prefill & prefix caching if supported. (#20930)
Signed-off-by: wang.yuqi <noooop@126.com>
2025-08-11 09:41:37 -07:00
Harry Mellor
c49848396d Refactor sliding window configuration to Transformers best practice (#21927)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-08-09 20:50:48 -07:00
Harry Mellor
56186474f6 [Docs] Reduce noise in docs and --help from the JSON tip (#22567)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-08-09 08:31:32 -07:00
Harry Mellor
e3edc0a7a8 Extract CompilationConfig from config.py (#22524)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-08-08 16:34:25 -07:00
Harry Mellor
7e3a8dc906 Remove from_dict from SpeculativeConfig (#22451)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-08-07 10:13:04 -07:00
Cyrus Leung
139d155781 [Frontend] Use engine argument to control MM cache size (#22441)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-07 09:47:10 -07:00
Cyrus Leung
766bc8162c [Core] Store only the keys for multi-modal data in P0 (#22198)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-07 01:45:04 -07:00
Giancarlo Delfin
469b3ffaaa [V1] port xformers backend to v1 (#21342)
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
2025-08-05 10:04:46 -07:00
Giancarlo Delfin
aa7012eb6d Add tree attention backend for v1 (part 1) (#20401)
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
2025-08-03 22:13:26 -07:00
H
24d1dffbeb [executor] feat: add supports_pp attr to executors (#21786)
Signed-off-by: Haibin Lin <haibin.lin@bytedance.com>
2025-08-03 18:04:45 +08:00
Rui Qiao
4ac8437352 [Misc] Getting and passing ray runtime_env to workers (#22040)
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
2025-08-01 23:54:40 -07:00
Harry Mellor
2d7b09b998 Deprecate --disable-log-requests and replace with --enable-log-requests (#21739)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-08-01 17:16:37 +01:00
Harry Mellor
fb0e0d46fc Fix get_kwargs for case where type hint is list[Union[str, type]] (#22016)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-08-01 05:26:42 -07:00
Dipika Sikka
dfbc1f8880 [Speculative Decoding] Add speculators config support (#21345) 2025-08-01 08:25:18 -04:00
Cyrus Leung
b4e081cb15 [Bugfix] Disable multi-modal preprocessor cache for DP (#21896)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-01 08:03:56 +01:00
Michael Goin
61445453df [UX] Rename CUTLASS_MLA_VLLM_V1 to CUTLASS_MLA (#21966)
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-07-30 20:40:34 -07:00
Yong Hoon Shin
ad510309ee Override attention metadata for fast prefill in some KV sharing setups (#21590)
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
2025-07-30 08:54:15 -07:00
Reza Barazesh
37efc63b64 [V0 deprecation] Guided decoding (#21347)
Signed-off-by: Reza Barazesh <rezabarazesh@meta.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-07-29 03:15:30 -07:00
Harry Mellor
94b71ae106 Use metavar to list the choices for a CLI arg when custom values are also accepted (#21760)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-07-28 19:31:10 +00:00
Cyrus Leung
86ae693f20 [Deprecation][2/N] Replace --task with --runner and --convert (#21470)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-07-27 19:42:40 -07:00
Maximilien de Bayser
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
22quinn
610852a423 [Core] Support model loader plugins (#21067)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
2025-07-24 01:49:44 -07:00
Robert Shaw
d5b981f8b1 [DP] Internal Load Balancing Per Node [one-pod-per-node] (#21238)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2025-07-23 20:57:32 -07:00
Michael Goin
82ec66f514 [V0 Deprecation] Remove Prompt Adapters (#20588)
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-07-23 16:36:48 -07:00
Lu Fang
accac82928 [Sampler] Introduce logprobs mode for logging (#21398)
Signed-off-by: Lu Fang <lufang@fb.com>
2025-07-23 01:39:25 -07:00
Kebe
bc8a8ce5ec [Misc] Remove deprecated args in v0.10 (#21349)
Signed-off-by: Kebe <mail@kebe7jun.com>
2025-07-22 05:26:39 -07:00
Konrad Zawora
c17231e827 Fix kv_cache_dtype handling for out-of-tree HPU plugin (#21302)
Signed-off-by: Konrad Zawora <kzawora@habana.ai>
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
Co-authored-by: Chendi.Xue <chendi.xue@intel.com>
2025-07-21 23:35:14 -07:00
Li, Jiang
a15a50fc17 [CPU] Enable shared-memory based pipeline parallel for CPU backend (#21289)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2025-07-21 09:07:08 -07:00
Chengji Yao
3a1d8940ae [TPU] support fp8 kv cache quantization (#19292)
Signed-off-by: Chengji Yao <chengjiyao@google.com>
2025-07-20 03:01:00 +00:00
Sungjae Lee
da6579bf41 [CI/CD][bugfix]fix: error argument to loads has incompatible type (#21223)
Signed-off-by: Sungjae Lee <33976427+llsj14@users.noreply.github.com>
Signed-off-by: Sungjae Lee <sung-jae.lee@navercorp.com>
2025-07-19 05:16:48 -07:00