mooncake-track
/
dynamo
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,250 Commits 2 Branches 0 Tags 76 MiB
Commit Graph

3250 Commits

Author SHA1 Message Date
Keiven C f51ec24d6f
fix: test_router_decisions async fix race condition (#6084) 
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
 2026-02-09 17:12:31 -08:00
Keiven C 241cc7833a
feat: add NIXL check to sanity_check (#6087) 
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
 2026-02-09 17:11:37 -08:00
Keiven C 027d2653a5
feat: expose Python Prometheus metric via DynamoComponentMetrics (#5817) 
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
 2026-02-09 17:10:37 -08:00
William Arnold 56a1b6e314
feat: Add SGLang /engine weight update endpoints (#6094) 2026-02-10 01:03:45 +00:00
orangeng 98eb6b7e03
docs: Fix service name in port-forward command (#5527) 
Signed-off-by: Orange Ng <ngquanhao@outlook.com>
Co-authored-by: Neal Vaidya <nealv@nvidia.com>
 2026-02-09 16:04:34 -08:00
MatejKosec 67329d1023
fix: profiler deployment timeout handling for MoE models (#6086) 
Wrap wait_for_deployment_ready() in try/except TimeoutError for both prefill and decode profiling sweeps
On timeout: log error, record via add_profiling_error(), clean up the timed-out deployment, and continue to the next parallelization mapping
Previously, a single deployment timeout would crash the entire profiler job
 2026-02-09 15:57:59 -08:00
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
dagil-nvidia d14d6ff49b
docs: improve Fern sidebar titles, add guide subtitles, and replace ASCII diagrams with D2 (#6069) 
Signed-off-by: Dan Gil <dagil@nvidia.com>
Signed-off-by: dagil-nvidia <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Jonathan Tong <jt572@cornell.edu>
 2026-02-09 22:11:33 +00:00
dagil-nvidia d48de155db
docs: sync fern/ with local indexer default changes from #5941 (#6073) 
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-09 14:08:39 -08:00
dagil-nvidia 0ef41ffe03
refactor: use tempfile module instead of hardcoded /tmp paths (#5789) 
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-09 21:44:03 +00:00
dagil-nvidia 3c9ca3fcb2
chore: add --no-install-recommends to apt-get install commands (#5774) 
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-09 14:45:28 -06:00
dagil-nvidia 0b05c4c712
ci: add doc exclusions to all CI-triggering filter groups (#6020) 
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-09 14:44:39 -06:00
Vladislav Nosivskoy 7202ced7b4
fix: DeepSeek V3.2 chat template FC and SO support (#6034) 
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
 2026-02-09 10:57:47 -08:00
muskansh-google 4520b8f636
docs: Update command to build Dynamo + SGLang container (#5908) 
Signed-off-by: muskansh-google <muskansh@google.com>
Co-authored-by: Neal Vaidya <nealv@nvidia.com>
 2026-02-09 10:09:22 -08:00
Hongkuan Zhou 1585244bc7
fix: add watchdog timeout for sglang dsr1 recipe (#6076) 
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
 2026-02-09 09:38:04 -08:00
dagil-nvidia bf270c2825
refactor: optimize regex patterns in docs scripts (#5777) 2026-02-09 17:20:03 +00:00
Harrison Saturley-Hall 59d20d1e9c
ci: update premerge to check the cargo-deny ban list (#5699) 
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>
 2026-02-09 11:41:13 -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
Neal Vaidya 3d7182b80e
fix: read block size from vllm at runtime (#5713) 
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
 2026-02-07 22:36:25 +00:00
dagil-nvidia 2c3066bd5d
docs: full migration of docs/ to fern format in fern/ (#6050) 
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-06 19:25:02 -08:00
Konstantin Korolev d59b9d72ed
fix: reduce NATS consumer inactive_threshold from 1h to 2min (#5861) 
Signed-off-by: advpropsys <korolev.konstantin.v@gmail.com>
Co-authored-by: Yan Ru Pei <yanrpei@gmail.com>
 2026-02-07 03:02:45 +00:00
Yongming Ding 7c25f70291
feat(mocker): add optional KV cache allocation/eviction trace (#6052) 
Signed-off-by: Yongming Ding <yongmingd@nvidia.com>
Co-authored-by: Yan Ru Pei <yanrpei@gmail.com>
 2026-02-07 03:02:28 +00:00
Karen Chung 2bcbda19e4
fix: Router + SGLang DP testing (#6057) 2026-02-06 18:39:28 -08:00
Richard Huo 7d035afffb
docs: add notes and instruction for latest trtllm kvbm disagg (#6055) 2026-02-06 17:03:07 -08:00
Qi Wang 00ea11ff2c
feat: EC E/PD workflow in TRT-LLM (#5815) 2026-02-06 15:32:52 -08:00
Xavier Chang 410691dc97
fix: fix missing update DynamoComponentReady condition (#5051) 
Signed-off-by: Xavier Chang <xuzhengc@nvidia.com>
 2026-02-06 23:14:47 +00:00
Yan Ru Pei d00f96074b
docs: clarify the usage of LRU for mocker evictor (#6053) 
Signed-off-by: PeaBrane <yanrpei@gmail.com>
 2026-02-06 15:08:41 -08:00
ls-2018 4715005ba5
fix: operator chart imagePullPolicy (#4821) 
Signed-off-by: acejilam <acejilam@gmail.com>
Co-authored-by: dagil-nvidia <dagil@nvidia.com>
 2026-02-06 17:08:27 -06:00
jthomson04 8f80d4815b
feat: GB200 GPT-oss disagg recipe (#4954) 
Signed-off-by: jthomson04 <jothomson@nvidia.com>
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: dagil-nvidia <dagil@nvidia.com>
 2026-02-06 17:08:17 -06:00
KrishnanPrash e7936c2516
fix(sglang): remove apt-installed python3-blinker (#5995) 
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
 2026-02-06 17:07:40 -06:00
Ben Hamm 03eb296ea7
fix(recipes): correct GPU counts in DeepSeek-R1 READMEs (#5953) 2026-02-06 17:07:30 -06:00
akshatha-k fce8bbc250
docs: add quick start sections to KVBM and Router guides (#6043) 
Signed-off-by: akshatha-k <akshutk@gmail.com>
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Dan Gil <dagil@nvidia.com>
 2026-02-06 15:17:21 -06:00
Tushar Sharma 6401e34daf
ci: Transition deploy tests to pytest framework (#5874) 
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
 2026-02-06 21:09:34 +00:00
Julien Mancuso 5092a5d0f8
fix: downgrading opencontainers/runtime-spec version to fix compatibility issue with containerd (#6049) 
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
 2026-02-06 12:51:37 -08:00
Jacky 1ffa489ea1
refactor: Move --migration-limit flag from backend to frontend (#5918) 
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
 2026-02-06 20:50:55 +00:00
Anant Sharma 3842b24479
fix: update bytes crate version to latest (#6041) 
Signed-off-by: Anant Sharma <anants@nvidia.com>
 2026-02-06 15:11:04 -05:00
mohammedabdulwahhab 82a8d768a5
fix: remove envsubst for logging-dashboard.yaml to preserve Grafana template variables (#6045) 
Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
 2026-02-06 12:07:31 -08:00
Qi Wang f6dd90474b
feat: enable go-to-definition for dynamo.runtime, dynamo.nixl and external dependencies (#6026) 2026-02-06 12:01:29 -08:00
Ryan McCormick bed29a1600
docs: Update disagg and request flow design docs based on latest code (#5993) 2026-02-07 04:01:13 +08:00
Anant Sharma dde23cc6e0
ci: remove release branch docs deploy workflow (#6039) 
Signed-off-by: Anant Sharma <anants@nvidia.com>
 2026-02-06 14:39:23 -05:00
Julien Mancuso d44fcde27c
feat: update grove dependency to 0.1.0-alpha.6 (#6015) 
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
 2026-02-06 12:35:42 -07:00
Julien Mancuso e25b92b390
fix: fix ChReK go.mod stale dependencies (#6040) 
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
 2026-02-06 12:35:13 -07:00
Yan Ru Pei 9e33e3fa66
chore: clean ups in kv_router.rs (#6028) 
Signed-off-by: PeaBrane <yanrpei@gmail.com>
 2026-02-06 19:27:44 +00:00
dagil-nvidia 07db589583
docs: clean up toctree navigation and add disaggregated serving guide (#6024) 
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-06 13:20:36 -06:00
Jonathan Tong 219e5c456f
ci: add GitHub actions for linting and cutting versioned docs for Fern (#5524) 
Signed-off-by: Jont828 <jt572@cornell.edu>
 2026-02-06 11:01:09 -08:00
GuanLuo ac50dccf95
feat: batch process images in encode worker. Add qwen3 to supported models (#6021) 
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
 2026-02-06 10:51:37 -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
Dillon Cullinan b0f54344fe
fix: Fix clashing labels (#6038) 
Signed-off-by: Dillon Cullinan <dcullinan@nvidia.com>
 2026-02-06 13:35:36 -05:00
Hongkuan Zhou 74d3db65b1
fix: remove bash wrapper for vllm dsr1 recipe (#6035) 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-06 10:11:17 -08:00
Karen Chung 3a41825489
fix: Correctly pass DP rank from Dynamo router into vLLM engine (#6014) 2026-02-06 09:48:53 -08:00