mooncake-track
/
dynamo
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,944 Commits 2 Branches 0 Tags 76 MiB
Commit Graph

605 Commits

Author SHA1 Message Date
Sandeep Maddipatla 23c42d83ed
feat: Add support for cpu builds in dockerfiles (#7139) 
Signed-off-by: Sandeep Maddipatla <sandeep.maddipatla@intel.com>
 2026-03-13 11:15:22 -07:00
ZhengHongming888 1fc5026347
feat: enable intel XPU Dockerfile for Dev Target (#7134) 
Signed-off-by: Hongming Zheng <hongming.zheng@intel.com>
Co-authored-by: Zhan Xue <zhan.xue@intel.com>
 2026-03-13 00:24:29 -07:00
Tzu-Ling Kan dba69e0f2f
chore(deps): bump vLLM 0.16.0 → 0.17.1 (#7170) 
Signed-off-by: Tzu-Ling <tzulingk@nvidia.com>
 2026-03-12 20:44:11 -07:00
Yan Ru Pei f80ad6926a
feat(kv-router): package dynamo-kv-indexer binary via maturin [LLM-126] (#7194) 
Signed-off-by: PeaBrane <yanrpei@gmail.com>
 2026-03-12 21:33:11 +00:00
Anant Sharma 3f565053e0
chore: remove unused python dependencies (#7238) 
Signed-off-by: Anant Sharma <anants@nvidia.com>
 2026-03-12 15:28:57 -04:00
Harrison Saturley-Hall f842a8e474
ci: add a preliminary compliance scan to ci (#7289) 
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
 2026-03-12 15:22:59 -04:00
Ran Rubin da3546638b
chore: Modify Docker templates to support multi arch builds (#6936) 2026-03-12 16:31:42 +02:00
Harrison Saturley-Hall bb3f639311
chore: update aic to v0.7.0rc15 (#7273) 
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
 2026-03-11 23:29:23 -04:00
Graham King 4bd6299ba1
test: pytests able to run locally now (#7219) 
Signed-off-by: Graham King <grahamk@nvidia.com>
 2026-03-11 17:58:38 -04:00
Adit Ranadive 727d32d728
fix: Update UCX Ref for Performance (#7212) 
Signed-off-by: Adit Ranadive <aranadive@nvidia.com>
 2026-03-11 11:17:04 -04:00
Harrison Saturley-Hall 0f974b47d4
chore: update aiperf to 0.6.0 and aic v0.7.0rc14 (#7193) 
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
 2026-03-10 21:32:31 -04:00
Dmitry Tokarev 0c94f00f19
fix: curl - retry DNS failures too (#7009) 
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
 2026-03-10 19:48:52 -04:00
Biswa Panda 3c44b88e89
feat(perf): add frontend pipeline and tokio runtime perf metric definitions (#6731) 2026-03-10 21:04:02 +00:00
Anant Sharma 3cebc864f3
feat: split monolithic requirements.txt and remove test deps from runtime image (#6656) 
Signed-off-by: Anant Sharma <anants@nvidia.com>
 2026-03-10 20:05:12 +00:00
Harrison Saturley-Hall fc55f612f9
chore: bump aiperf and aiconfig to last RCs (#7138) 
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
 2026-03-09 21:40:37 -04:00
Harrison Saturley-Hall 3bfd0f9290
chore: bump AIC to 0.7.0rc12 (#7070) 
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
 2026-03-08 18:18:49 -04:00
Harrison Saturley-Hall f596945d53
chore: bump aic to v0.7.0rc11 (#7043) 
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
 2026-03-06 19:44:46 -05:00
Harrison Saturley-Hall 25393fb395
chore: bump trtllm to 1.3.0rc5.post1 (#7040) 
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
 2026-03-06 19:44:24 -05:00
Richard Huo 723676b426
fix: remove the aws-ofi-nccl plugin from linker cache in regular trtllm runtime image (#6944) 2026-03-05 17:49:43 -08:00
Ryan Olson 8cef50c653
chore: complete the migration from 1.90.0 to 1.93.1 (#6917) 
Signed-off-by: Ryan Olson <rolson@nvidia.com>
 2026-03-06 00:12:17 +00:00
Anant Sharma 6be2a9b15c
fix: add missing UCX/NIXL native libraries to sglang runtime (#6939) 
Signed-off-by: Anant Sharma <anants@nvidia.com>
 2026-03-05 17:07:36 -05:00
Kris Hung eb0bf24e82
feat: Add NVTX markers for vLLM EPD (#6627) 2026-03-04 17:29:00 -08:00
Keiven C c55f38dc16
docs: testing and container docs update (#6806) 
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
 2026-03-04 11:33:10 -08:00
Adit Ranadive 6d8b5c4e67
chore: Update AWS SDK version used (#6841) 
Signed-off-by: Adit Ranadive <aranadive@nvidia.com>
 2026-03-04 09:11:28 -08:00
Anant Sharma 550464b633
fix: exclude nixl .so files from ai-dynamo-runtime wheel (#6430) 
Signed-off-by: Anant Sharma <anants@nvidia.com>
 2026-03-04 11:55:25 -05:00
Graham King 4e1bd70080
fix(frontend): vllm processor works with stream_interval > 1 (#6816) 
Signed-off-by: Graham King <grahamk@nvidia.com>
 2026-03-04 13:52:18 +00:00
zxue2 e0a2e7bb71
feat: enable intel xpu dockerfile (#6109) 
Signed-off-by: Zhan Xue <zhan.xue@intel.com>
Co-authored-by: XinYu Ye <xinyu.ye@intel.com>
Co-authored-by: Hongming Zheng <hongming.zheng@intel.com>
 2026-03-04 01:40:21 -05:00
Keiven C a60cdf59ed
feat: optimize dev/local-dev Dockerfiles for source-based development (part 1) (#6743) 
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
 2026-03-03 17:45:58 -08:00
Anant Sharma 9254e3d4d2
chore: update nixl version to 0.10.1 (#6826) 
Signed-off-by: Anant Sharma <anants@nvidia.com>
 2026-03-03 16:47:55 -05:00
jthomson04 9e5014da07
perf: Concurrent router perf improvements (#6536) 
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
 2026-02-28 21:55:50 +00:00
Nate Mailhot 64082ccd3a
chore: upgrade nixl to 0.10.0 (#6685) 2026-02-27 13:01:07 -08:00
Alec 64574a3e0f
chore(deps): bump vLLM to 0.16.0 (#6614) 
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-26 21:09:21 +00:00
dagil-nvidia 7ce74a63b0
docs: fix rendered.Dockerfile path in container README (#6643) 
Signed-off-by: Dan Gil <dagil@nvidia.com>
 2026-02-26 14:58:19 -06:00
Jason Zhou ab63b8b669
chore: update aiconfigurator commit to use AIC 0.7.0 RC5 (#6618) 2026-02-26 10:04:15 -08:00
Rafi Wiener c7569efdef
fix: add TRITON_*_PATH env vars to vLLM runtime Dockerfile (#6401) 
Signed-off-by: Rafi Wiener <rwiener@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: dagil-nvidia <dagil@nvidia.com>
 2026-02-26 02:49:55 +00:00
Hongkuan Zhou 4c648b11e9
refactor: move core logics of DPP -> AIC and support static profiling (#6285) 
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Co-authored-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>
 2026-02-26 00:39:50 +00:00
Anant Sharma 6608cd5947
fix: stage sccache off PATH to prevent meson auto detection (#6578) 
Signed-off-by: Anant Sharma <anants@nvidia.com>
 2026-02-25 16:01:44 -05:00
Yuewei Na 8483e4a07f
chore: Upgrade to tensorrt-llm==1.3.0rc5 (#6579) 
Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
 2026-02-25 12:22:58 -08:00
Anant Sharma 73c02a0b4a
fix: disable media-ffmpeg feature by default (#6574) 
Signed-off-by: Anant Sharma <anants@nvidia.com>
 2026-02-25 11:49:58 -05:00
Ran Rubin 8fbe722895
chore: bake sccache into dynamo base (#6532) 2026-02-25 09:50:07 +02:00
Jason Zhou 4ea80e9585
chore: use aic release/0.7.0 (#6494) 2026-02-24 16:27:19 -06:00
ishandhanani 6642e23e0f
feat: sglang to 0.5.9 + updated docs (#6518) 
Co-authored-by: baihuitian <baihuitian.bht@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-24 21:48:25 +00:00
Keiven C f89088007e
fix: vLLM Dockerfile need nvlink and crt for kvbm dependencies (#6521) 
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-24 13:28:44 -08:00
Ayush Agarwal e94f464760
chore: install vllm-omni in vllm container (#6458) 
Signed-off-by: ayushag <ayushag@nvidia.com>
 2026-02-24 21:03:53 +00:00
Anant Sharma 0f47842ac7
ci: switch container-validation-dynamo to runtime target (#6499) 
Signed-off-by: Anant Sharma <anants@nvidia.com>
 2026-02-24 09:42:41 -05:00
Keiven C 6d3e0137cf
fix: add missing nvlink binary to vLLM and TRT-LLM runtime/dev/local-dev Dockerfiles (#6503) 
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-23 18:33:19 -08:00
William Zhang a798e08c81
fix: Fix dev container build (#6455) 
There were 2 bugs prior to this commit when building a TRTLLM dev
container:

- template rendering bug
- CUDA compatibility layer

The `nvidia_entrypoint.sh` script should render the second completely
unnecessary.
 2026-02-20 11:49:04 -08:00
KrishnanPrash 0688d5843a
docs: Fix Dockerfile path in README for vLLM dev image (#6429) 
Signed-off-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com>
 2026-02-19 11:34:58 -08:00
Yuewei Na 9a15730a7f
chore: Upgrade to tensorrt-llm==1.3.0rc3 (#6402) 
Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: dagil-nvidia <dagil@nvidia.com>
 2026-02-19 14:12:32 -05:00
Tushar Sharma 741c20bf6c
fix: move ffmpeg copy before USER dynamo to fix permission denied (#6260) 
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>
 2026-02-19 17:45:36 +00:00