vraiti
79f8c5bd8c
[Metrics] Scope unregister_vllm_metrics() to strictly "vllm:" metrics ( #42331 )
...
`unregister_vllm_metrics()` currently uses "vllm" in `collector._name` to decide
which collectors to remove from the Prometheus registry, removing every even
metrics registered by other subsystems or downstream extensions like "vllm_omni:"
Signed-off-by: vraiti <vraiti@redhat.com >
Signed-off-by: Mark McLoughlin <markmc@redhat.com >
2026-06-11 15:43:14 +00:00
Jiangyun Zhu
f81daf8880
[Attention] add triton diff-kv backend for mimo ( #41797 )
...
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com >
2026-06-11 11:36:31 -04:00
Nick Hill and Claude Opus 4.8
4085ff7cb4
[Core] Add kvcache watermark to reduce preemptions ( #44594 )
...
Signed-off-by: Nick Hill <nickhill123@gmail.com >
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-11 08:27:31 -07:00
fangyuchu and Tyler Michael Smith
23eb7c8fbb
[Bugfix] Fix NixlEPAll2AllManager's dependency on --enable-elastic-ep to function ( #44422 )
...
Signed-off-by: fangyuchu <fangyuchu@qq.com >
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com >
2026-06-11 08:14:49 -07:00
wineandchord
c2b4cd39ac
[Doc][Attention] Fix MLA top-of-file comments ( #37047 )
...
Signed-off-by: wineandchord <guoqizhou19@gmail.com >
2026-06-11 08:14:45 -07:00
Kai K.
f1d8d99717
[Bugfix] CohereModel.load_weights: skip modelopt _quantizer.* keys ( #43495 )
...
Signed-off-by: Kai Köhler <kai.koehler@web.de >
2026-06-11 08:14:21 -07:00
Nicolò Lucchesi
750aab5b8e
[Bugfix] Fix CPU memory leak related to not cleaning up old remotes data ( #44424 )
...
Signed-off-by: NickLucche <nlucches@redhat.com >
2026-06-11 07:54:52 -07:00
Michael Goin and Claude
5edf7ff489
[Core] Release cached device memory under pressure on UMA GPUs during weight loading ( #45179 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
Co-authored-by: Claude <noreply@anthropic.com >
2026-06-11 17:49:50 +03:00
Natalie Lin and Harry Mellor
b78fc47f05
[Docs] Add redirect for moved lmcache examples page ( #45218 )
...
Signed-off-by: nataliepjlin <nataliepjlin@gmail.com >
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2026-06-11 10:41:08 -04:00
Harry Mellor
03878d1c22
Deprecations for v0.23 and v0.24 ( #44992 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2026-06-11 14:35:38 +00:00
55911db580
[PD][Core] Fix Mamba prefix cache hit rate in PD disaggregation ( #44243 )
...
Co-authored-by: lHrHenry233 <2381623149@qq.com >
Co-authored-by: underfituu <hzhucong@163.com >
Signed-off-by: Zhanqiu Hu <zhu@redhat.com >
2026-06-11 14:10:25 +00:00
cc640ee8bc
[Rust Frontend][Metrics] Export vllm:lora_requests_info from frontend ( #45030 )
...
Signed-off-by: Will Eaton <weaton@redhat.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-11 06:45:03 -07:00
Fynn Schmitt-Ulms and mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
ebc6ef971a
Hidden states extraction improvements ( #43805 )
...
Signed-off-by: Fynn Schmitt-Ulms <fschmitt@redhat.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-11 09:44:45 -04:00
tc-mb
ab3a1fd2e6
minicpmv4_6: fix ImageSize (W,H) order for placeholder token calculation ( #45244 )
...
Signed-off-by: tc-mb <tianchi_cai@icloud.com >
2026-06-11 13:43:56 +00:00
Itay Etelis and Itay Etelis
c3662b36ea
[KV offload] Parallel-agnostic fs-tier cache for single full-attention group ( #44733 )
...
Signed-off-by: Itay Etelis <itay.etelis@ibm.com >
Co-authored-by: Itay Etelis <itay.etelis@ibm.com >
2026-06-11 15:48:37 +03:00
Juan Pérez de Algaba
e62d00ab73
docs: add fix disclosure policy to SECURITY.md ( #45253 )
...
Signed-off-by: jperezde <jperezde@redhat.com >
2026-06-11 12:48:00 +00:00
Yufeng He and Wentao Ye
1f60771c74
fix: guard flash-attn rotary import ( #42679 )
...
Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com >
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com >
2026-06-11 08:43:31 -04:00
Richard Barnes and Shengqi Chen
05d9848267
[Build] Upgrade CUDA Dockerfiles from GCC 10 to GCC 12 for C++20 compatibility ( #44923 )
...
Signed-off-by: Richard Barnes <rbarnes@meta.com >
Co-authored-by: Shengqi Chen <harry-chen@outlook.com >
2026-06-11 12:26:52 +00:00
jasen
ef67071b21
[Build] Skip spinloop extension on Python < 3.11 ( #44783 )
...
Signed-off-by: Jasen2201 <yajizhan@amd.com >
2026-06-11 11:23:21 +00:00
x41lakazam
3508cb78d4
[Bugfix] Fix broken profile_modular_kernel.py ( #43300 )
2026-06-11 12:17:23 +01:00
Harry Mellor
432905d5d6
Only enable PR docs builds manually ( #45262 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2026-06-11 03:14:29 -07:00
Ting SUN and Bugen Zhao
1f9dd7900d
[Bugfix][Rust Frontend] Validate out-of-vocab token ids in request params ( #44680 )
...
Signed-off-by: Ting Sun <suntcrick@gmail.com >
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
2026-06-11 03:14:11 -07:00
Juan Pérez de Algaba and mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
9492362972
[Security] Apply sanitize_message to Anthropic and STT error paths ( #45119 )
...
Signed-off-by: jperezde <jperezde@redhat.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-11 10:05:34 +00:00
7852e50e4d
[docs] Document --scheduler-cls base class requirement (extend AsyncScheduler, not Scheduler) ( #43724 )
...
Signed-off-by: Georgii Kliukovkin <kliukovkin@gmail.com >
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com >
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2026-06-11 10:49:51 +01:00
Reid
0d657e44dc
[Rust Frontend] Fix DeepSeek V3.2 continue_final_message rendering ( #45155 )
...
Signed-off-by: reidliu41 <reid201711@gmail.com >
2026-06-11 09:34:19 +00:00
王金旭 and Cursor
aa1df36c53
Fix/minicpmv46 missing version ( #44980 )
...
Signed-off-by: wjinxu <1299461899@qq.com >
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-06-11 09:20:45 +00:00
wcy and lyd1992
f06aefb4e3
[CPU] Add missing scalar fallback for CPU W4A8 INT4 GEMM ( #44523 )
...
Signed-off-by: wcy <233313160abc@gmail.com >
Co-authored-by: lyd1992 <liuyudong@iscas.ac.cn >
2026-06-11 08:52:01 +00:00
Julien Denize
1c3a72b8b2
[Bugfix] Add fetch_images to MistralCommonImageProcessor ( #45180 )
...
Signed-off-by: juliendenize <julien.denize@mistral.ai >
2026-06-11 16:13:01 +08:00
Juan Pérez de Algaba
d598d23973
[Security] Reject non-finite temperature and repetition_penalty values ( #45116 )
...
Signed-off-by: jperezde <jperezde@redhat.com >
2026-06-11 01:12:14 -07:00
Juan Pérez de Algaba
f219788f91
[Security] Fix info disclosure via int32 truncation in GGUF dequantize kernels ( #44971 )
...
Signed-off-by: jperezde <jperezde@redhat.com >
2026-06-11 08:05:14 +00:00
Chris Leonard and Shengqi Chen
6e64c1bab1
[10c/n] Migrate MoE kernels to torch stable ABI ( #44565 )
...
Signed-off-by: Chris Leonard <chleonar@redhat.com >
Co-authored-by: Shengqi Chen <harry-chen@outlook.com >
2026-06-10 23:02:26 -07:00
Kevin H. Luu
2f2c5cf4f1
[release] Always block release images to dockerhub ( #45236 )
...
Signed-off-by: Kevin H. Luu <khluu000@gmail.com >
2026-06-10 22:53:04 -07:00
Mohammad Miadh Angkad
40e065e86a
[Docker] Fix CUTLASS DSL cu13 install order in Dockerfile ( #45204 )
...
Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com >
2026-06-11 05:19:36 +00:00
Yuanyuan Chen and Li, Jiang <jiang1.li@intel.com>
0b995f8609
Use std::bit_cast for type punning in CPU kernels ( #45089 )
...
Signed-off-by: Yuanyuan Chen <cyyever@outlook.com >
Co-authored-by: Li, Jiang <jiang1.li@intel.com >
2026-06-10 22:07:44 -07:00
Bugen Zhao
43914dd743
[Rust Frontend] Add Python bridge for Rust tool parsers ( #44624 )
...
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-06-11 04:51:06 +00:00
Prajjwal Chittori and Shengqi Chen
3501324957
[Build] fix self-contradictory precompiled-flag orthogonality test ( #44942 )
...
Signed-off-by: pjdurden <prajjwalchittori1@gmail.com >
Co-authored-by: Shengqi Chen <harry-chen@outlook.com >
2026-06-11 12:49:08 +08:00
Flora Feng
3a04061701
[Refactor][Parser] Unify Response API to use parser.parse() like Chat Completion API ( #45190 )
...
Signed-off-by: sfeng33 <4florafeng@gmail.com >
2026-06-11 04:37:51 +00:00
Yifan Qiao
f272dfdce1
[KV Connector] Mooncake store: prefix-cache retention interval for sparse attention ( #44774 )
2026-06-10 21:36:34 -07:00
velonica0
f31bc2ea60
[CPU][RISC-V] Enable oneDNN W8A8 INT8 to run on RISC-V ( #44478 )
...
Signed-off-by: velonica0 <like@mail.nankai.edu.cn >
2026-06-11 04:09:05 +00:00
ankrovv and Flora Feng
248e33c40d
[Bugfix][Responses API] Set id on function_call item in streaming done event ( #44608 )
...
Signed-off-by: Aniruddh Krovvidi <aniruddh.krovvidi@oracle.com >
Co-authored-by: Flora Feng <4florafeng@gmail.com >
2026-06-11 03:52:42 +00:00
Bugen Zhao
5d5591d99b
[Rust Frontend] Populate cached_token_count in responses ( #44887 )
...
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-06-10 20:50:05 -07:00
Wentao Ye
85a0ffae42
[CI Bug] Remove qwen test ValueError: No example model defined for Qwen/Qwen-7B-Chat ( #45194 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com >
2026-06-10 20:11:00 -07:00
Harry Mellor
18d87a87dc
Deprecate Transformers v4 support ( #45161 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2026-06-11 11:04:01 +08:00
Flora Feng
b038a2f73b
[CI][Bugfix] Update Dockerfile dependency graph PNG ( #45209 )
...
Signed-off-by: sfeng33 <4florafeng@gmail.com >
2026-06-10 19:40:25 -07:00
Ting SUN
2d481f8a94
[Bugfix][Rust Frontend] Stop unescaping XML-style tool-call parameter values ( #45025 )
...
Signed-off-by: Ting Sun <suntcrick@gmail.com >
2026-06-10 19:05:23 -07:00
Rohan Potdar and Andreas Karatzas
7920ccb97c
[Bugfix]: Fix Quark gpt-oss weight loading broken by FusedMoe refactor ( #45067 )
...
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com >
Co-authored-by: Andreas Karatzas <akaratza@amd.com >
2026-06-10 18:17:46 -07:00
Wentao Ye
86111c00c7
[Chore] Add Github notification for MRv2 for @yewentao256 ( #45191 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com >
2026-06-11 09:01:49 +08:00
qizixi
e2db0222e9
[Perf][Attention] Pin MLA chunked-context metadata tensors so H2D copies are truly non-blocking ( #45074 )
...
Signed-off-by: zixi-qi <zixi@inferact.ai >
2026-06-10 15:56:49 -07:00
82d6b59f04
[CI/Build] Skip test_use_trtllm_attention on non-CUDA platforms ( #44687 )
...
Signed-off-by: Dan Blanaru <48605845+DanBlanaru@users.noreply.github.com >
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-10 18:18:42 -04:00
Andreas Karatzas
16282a9c4e
[ROCm][CI] Moving MI300 tests to MI325 until cluster is stabilized ( #45170 )
...
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
2026-06-10 20:26:17 +00:00