Ayush Agarwal
|
9f76d0606c
|
feat: text to image vLLM Omni (#5912)
Signed-off-by: ayushag <ayushag@nvidia.com>
|
2026-02-09 18:19:27 -05:00 |
|
Yan Ru Pei
|
6783bdcaa9
|
chore: enable local indexers by default, and use normal event plane by default (not jetstream) (#5941)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
|
2026-02-08 20:48:02 +00:00 |
|
Qi Wang
|
00ea11ff2c
|
feat: EC E/PD workflow in TRT-LLM (#5815)
|
2026-02-06 15:32:52 -08:00 |
|
Yan Ru Pei
|
3e41702211
|
chore: remove and unify bindings in kv.rs (#6016)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
|
2026-02-06 18:44:46 +00:00 |
|
dagil-nvidia
|
b19de4ed77
|
docs: cleanup of docs refactor for components, integrations, and features (#6019)
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-02-05 19:50:17 -08:00 |
|
akshatha-k
|
80e7bafd37
|
docs: Migrate router documentation to three-tier structure (#5979)
Signed-off-by: akshatha-k <akshutk@gmail.com>
Signed-off-by: dagil-nvidia <dagil@nvidia.com>
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: dagil-nvidia <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-02-06 01:55:50 +00:00 |
|
Indrajit Bhosale
|
a72f41f604
|
fix: Update vllm multimodal PD Disagg launch script (#5951)
|
2026-02-05 19:33:04 +00:00 |
|
Ryan McCormick
|
910d74f59e
|
fix: Add mpi arg to all srun commands (#5948)
|
2026-02-04 17:08:54 -08:00 |
|
dagil-nvidia
|
ef292944fd
|
docs: fix markdown formatting in Distributed_Inference README (#5947)
|
2026-02-04 15:08:18 -06:00 |
|
Hongkuan Zhou
|
0c0336e6ea
|
feat: Add per-worker Prometheus metrics for router load monitoring (#5842)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
|
2026-02-04 11:51:43 -08:00 |
|
Ayush Agarwal
|
76e0e2076b
|
feat: basic vllm omni pipeline support (#5608)
Signed-off-by: ayushag <ayushag@nvidia.com>
|
2026-02-04 18:35:41 +00:00 |
|
Sean SH Choi
|
3b9b3f31c0
|
fix: Add --is-decode-worker flag to vllm examples (#5899)
Signed-off-by: Sean Choi <sechoi@nvidia.com>
|
2026-02-03 07:25:14 +00:00 |
|
dagil-nvidia
|
6720dfb658
|
docs: fix SGLang docs links (docs.sglang.ai → docs.sglang.io) (#5894)
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-02-03 04:29:57 +00:00 |
|
Keiven C
|
f597b75b3e
|
chore: remove NIM custom backend example (part 1, docs only) (#5891)
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
|
2026-02-02 17:15:33 -08:00 |
|
kYLe
|
6e568d4552
|
docs: Modify AI configurator command in README (#5820)
Signed-off-by: kYLe <kylhuang@nvidia.com>
Signed-off-by: Kyle Huang <kylhuang@nvidia.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>
|
2026-02-02 18:54:55 -05:00 |
|
Yan Ru Pei
|
ef1078e46e
|
chore: nuke standalone fast api router (#5845)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
|
2026-01-30 16:42:21 -08:00 |
|
hhzhang16
|
6c8708104e
|
fix: add --is-decode-worker flag (#5843)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
|
2026-01-30 16:20:00 -08:00 |
|
Julien Mancuso
|
f6d6b34e87
|
fix: update docker-compose path in doc (#5821)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
|
2026-01-30 21:24:53 +00:00 |
|
Julien Mancuso
|
9e2a2cc9e6
|
feat: add epp component (#5611)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
|
2026-01-29 22:43:01 +00:00 |
|
Neal Vaidya
|
c5bb8df685
|
fix: specifiy triton worker dynamo base [DYN-1984] (#5794)
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
|
2026-01-29 11:51:44 -08:00 |
|
Indrajit Bhosale
|
842f0f15ec
|
fix: VLLM Multimodal minor fixes (#5748)
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
|
2026-01-29 02:45:41 +00:00 |
|
GuanLuo
|
77aadb722f
|
chore: adjust gpu-memory-utilization to accommodate vLLM's runtime GPU memory requirement (#5755)
Signed-off-by: Guan Luo <gluo@nvidia.com>
|
2026-01-28 23:48:48 +00:00 |
|
Hongkuan Zhou
|
d1697dc34e
|
feat: add DGD example for global router + vllm (#5760)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
|
2026-01-28 15:18:33 -08:00 |
|
Hongkuan Zhou
|
8ebfd1e4e7
|
feat: global router for hierarchical planner (#5697)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
|
2026-01-27 19:01:34 -08:00 |
|
GuanLuo
|
903f818498
|
chore: add multimodal image benchmark scripts for performance evaluation (#5509)
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
|
2026-01-27 17:39:58 -08:00 |
|
Nate Mailhot
|
9c71f28634
|
fix: link checking (#5209)
|
2026-01-27 10:47:26 -08:00 |
|
Abhishek Gupta
|
912a4d4b7e
|
docs: add NIXL backend configuration and fix multiple typos (#5564)
Signed-off-by: Abhishek Kumar Gupta (AbhiOnGithub)
Signed-off-by: Abhishek Kumar Gupta <mail2abhishekgupta@gmail.com>
Co-authored-by: dagil-nvidia <dagil@nvidia.com>
|
2026-01-23 16:43:46 -08:00 |
|
Yan Ru Pei
|
feb6d272ac
|
chore: nuke ForwardPassMetrics (#5531)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
|
2026-01-23 16:26:01 +00:00 |
|
Yan Ru Pei
|
03162161e4
|
chore: default python hash seed to zero always for the engines (#5583)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
|
2026-01-22 17:20:24 -08:00 |
|
Indrajit Bhosale
|
66963b7040
|
feat: Standalone encoder in dynamo trtllm (#4668)
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
Signed-off-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com>
Co-authored-by: Krishnan Prashanth <kprashanth@nvidia.com>
Co-authored-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com>
|
2026-01-22 23:49:19 +00:00 |
|
Ayush Agarwal
|
91ddf4189b
|
feat: v0 diffusion handler support (#5533)
Signed-off-by: ayushag <ayushag@nvidia.com>
|
2026-01-21 22:25:54 +00:00 |
|
Neal Vaidya
|
971c30692e
|
feat: triton worker example (#4971)
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
|
2026-01-16 12:53:09 -08:00 |
|
Ayush Agarwal
|
f9918f615f
|
chore: support for muliple MM requests for vLLM Encoder + Rust Based Preprocessor (#5463)
Signed-off-by: ayushag <ayushag@nvidia.com>
|
2026-01-16 20:48:49 +00:00 |
|
KrishnanPrash
|
ddee21cbe1
|
feat: SGLang aggregated multimodal support (#5450)
|
2026-01-16 00:36:10 -08:00 |
|
Biswa Panda
|
7ebd5f8266
|
feat: [router] serve worker KV query over dynamo endpoint instead of nats (#5451)
|
2026-01-15 19:59:33 +00:00 |
|
Neal Vaidya
|
332da40075
|
fix: update hello_world example to remove etcd (#5422)
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
|
2026-01-14 10:54:16 -08:00 |
|
Graham King
|
c5458b9954
|
chore(router): Remove deprecated best_worker_id and metrics_labels (#5412)
Signed-off-by: Graham King <grahamk@nvidia.com>
|
2026-01-14 16:20:42 +00:00 |
|
jh-nv
|
e22bb0376f
|
fix: Properly handle multiple text components from request (#5196)
|
2026-01-14 11:13:22 -05:00 |
|
GuanLuo
|
334cbd9b82
|
refactor: vllm EPD refactor (#4994)
Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
|
2026-01-14 01:23:11 -08:00 |
|
jh-nv
|
8c129ed472
|
feat: Propagate OTEL tracing context for trtllm (#5377)
|
2026-01-13 13:34:30 -05:00 |
|
Biswa Panda
|
869562da20
|
feat: add examples for kv state approximation based routing (#5320)
|
2026-01-13 10:24:17 -08:00 |
|
hhzhang16
|
c8770464ab
|
feat: normalize dynamo namespace computation (#5231)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
|
2026-01-12 19:09:43 +00:00 |
|
Indrajit Bhosale
|
5cd8005c45
|
fix: Fix decode worker in vllm for qwen_vl models (#5281)
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
Co-authored-by: Krishnan Prashanth <kprashanth@nvidia.com>
|
2026-01-09 12:51:10 -08:00 |
|
Hongkuan Zhou
|
2e381b3e6a
|
fix: remove unused prometheus port args in trtllm planner DGD (#5314)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
|
2026-01-09 10:01:08 -08:00 |
|
dagil-nvidia
|
c29f78c19d
|
docs: add host and bootstrap port to disagg multinode example (#5309)
Signed-off-by: Dan Gil <dagil@nvidia.com>
|
2026-01-09 15:31:09 +00:00 |
|
Biswa Panda
|
0d3ff44000
|
fix: enable toggling kv events pub/sub (currently nats based) with --no-kv-events flag (#5237)
|
2026-01-09 06:36:51 +00:00 |
|
Wenqi Glantz
|
6f9619a210
|
feat(vllm): Add prompt embeds support for pre-computed inference inputs (#4739)
Signed-off-by: Wenqi Glantz <wglantz@nvidia.com>
|
2026-01-08 20:03:10 +00:00 |
|
Qi Wang
|
1efc41e0a5
|
fix: avoid example TRT-LLM worker OOM by tuning params (#5250)
|
2026-01-07 13:52:39 -08:00 |
|
Nate Mailhot
|
c4c2cc930d
|
fix: broken symlinks (#5235)
|
2026-01-07 12:16:30 -08:00 |
|
Ayush Agarwal
|
85e0512f3e
|
feat: ec connector handler (#5162)
Signed-off-by: Ayush Agarwal <ayushag@nvidia.com>
|
2026-01-07 11:27:04 -08:00 |