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

77 Commits

Author SHA1 Message Date
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
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
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
Karen Chung b5c0db63c3
feat: TRTLLM DP Rank Routing (#5936) 2026-02-05 17:43:04 -08:00
dagil-nvidia 3023c6258a
docs: migrate Profiler docs to three-tier structure (#6003) 
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>
 2026-02-05 18:05:49 -06:00
akshatha-k 4c3eba2aeb
docs: restructure KVBM documentation into three-tier format (#5905) 
Signed-off-by: akshatha-k <akshutk@gmail.com>
Signed-off-by: Dan Gil <dagil@nvidia.com>
Signed-off-by: dagil-nvidia <dagil@nvidia.com>
Co-authored-by: dagil-nvidia <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Kyle McGill <101670481+nv-kmcgill53@users.noreply.github.com>
 2026-02-05 18:02:05 -06:00
dagil-nvidia 8aa7335e35
docs: migrate Speculative Decoding docs to three-tier structure (#6001) 
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-05 17:45:10 -06:00
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
Yuewei Na e2982e1f5a
fix(docs): remove trailing transition causing Sphinx build failure (#5831) 
Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
 2026-01-30 12:51:26 -08:00
Yuewei Na 284f772b25
docs: add known issues section for TRT-LLM backend (#5801) 
Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Signed-off-by: Yuewei Na <248773860+nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
 2026-01-30 11:21:28 -08:00
Richard Huo 8cdfe68242
docs: fix the statements for setting up the trtllm NIXL backends (#5763) 2026-01-29 08:15:45 -08:00
ishandhanani ed5e4fd021
docs: remove incorrect HighConfidence dLLM algorithm reference (#5723) 
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-28 08:16:08 -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
Ayush Agarwal 91ddf4189b
feat: v0 diffusion handler support (#5533) 
Signed-off-by: ayushag <ayushag@nvidia.com>
 2026-01-21 22:25:54 +00:00
Anish 0d597e7c55
docs: Documentation audit and updates for 0.8 (#5380) 
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Dan Gil <dagil@nvidia.com>
 2026-01-15 00:23:09 +00:00
Neelay Shah 52ce68e60b
docs: Fix KV cache transfer UCX configuration instructions (#5247) 
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-12 13:06:04 -08:00
dagil-nvidia 4f6996c733
docs: fix broken documentation links (#5330) 2026-01-09 17:34:41 -06:00
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
ishandhanani 5a158552db
fix: remove old docs and unify model paths (#5179) 2026-01-05 19:27:44 +00:00
Tushar Sharma cf433e6825
chore: update all copyright headers in repo to 2026 (#5130) 
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
 2026-01-02 22:08:23 +00:00
Yan Ru Pei 0055f2a471
docs: remove stale router diagram in trtllm docs (#5034) 
Signed-off-by: PeaBrane <yanrpei@gmail.com>
 2025-12-19 18:20:55 +00:00
Keiven C 4d0b1a119e
docs: document LMCache Prometheus metrics harmless error for vLLM 0.12.0 (#5026) 
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
 2025-12-19 08:57:40 -08:00
Tanmay Verma e1c685b105
fix: Remove debug logging from aiperf benchmarking (#5010) 2025-12-18 02:34:41 +00:00
Neal Vaidya 3c4b3069d2
docs: consolidate multimodal docs (#4842) 
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
 2025-12-16 02:08:58 +00:00
Yan Ru Pei 8711237357
docs: router cost function mermaid (#4943) 
Signed-off-by: PeaBrane <yanrpei@gmail.com>
 2025-12-13 07:13:58 +00:00
Dmitry Tokarev 525030324e
chore: TRTLLM 1.2.0rc4 (#4836) 
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
 2025-12-11 03:02:24 +00:00
J Wyman 96fe63fe2e
feat: nixl_connect: Improve Concurrency Support (#4433) 
Signed-off-by: J Wyman <jwyman@nvidia.com>
 2025-12-09 17:29:22 -05:00
Indrajit Bhosale 94d145a9b4
docs: Add multimodal documentation vllm, sglang, and trtllm backends (#4510) 
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
Co-authored-by: krishung5 <krish@nvidia.com>
 2025-12-09 23:38:31 +08:00
Anant Sharma 8b197406b4
fix: move new launch script to examples (#4800) 
Signed-off-by: Anant Sharma <anants@nvidia.com>
 2025-12-08 20:27:54 +00:00
Dilreet Raju f315374fdc
docs: Guide for Speculative Decoding in VLLM using Eagle3 and Meta-Llama-3.1-8B-Instruct (#3895) 
Signed-off-by: DilreetRaju <dilreetraju@gmail.com>
 2025-12-05 21:09:38 +00:00
William Arnold 3bc129dc37
feat: Add python-configurable engine routes for sglang profiling (#4617) 
Signed-off-by: William Arnold <7565007+Aphoh@users.noreply.github.com>
 2025-12-05 10:28:36 -08:00
dagil-nvidia d5a75dd8c5
docs: update TensorRT-LLM commit for multimodal EPD to v1.2.0rc3 (#4713) 
Signed-off-by: Dan Gil <dagil@nvidia.com>
 2025-12-03 18:18:28 +00:00
Keiven C c6555852ee
fix: enable LMCache metrics visibility with PROMETHEUS_MULTIPROC_DIR (#4654) 
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
 2025-12-02 18:47:30 -08:00
Tanmay Verma c9d7d95f4b
chore: Upgrade to tensorrt-llm==1.2.0rc3 (#4645) 2025-11-26 22:53:41 -08:00
dagil-nvidia 2e5e68b4ff
docs: remove build container instructions from trtllm multimodal example (#4624) 
Signed-off-by: Dan Gil <dagil@nvidia.com>
Signed-off-by: dagil-nvidia <dagil@nvidia.com>
 2025-11-26 10:29:31 -06:00
Tanmay Verma 6cd6033c7c
docs: Fix the documentation for NIXL kv cache transfer backend (#4611) 2025-11-26 08:46:10 -06:00
dagil-nvidia 93c8142080
docs: update TensorRT-LLM commit for NIXL to v1.2.0rc2 (#4582) 
Signed-off-by: Dan Gil <dagil@nvidia.com>
 2025-11-25 09:19:31 -06:00
Indrajit Bhosale 550bf98ce2
feat: Add security flag to MM flow in vllm (#4556) 
Co-authored-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com>
 2025-11-25 02:01:38 +00:00
Ziqi Fan 6d69e8c7b0
chore: unify LMCache UX w/ and w/o Dynamo (#4509) 
Signed-off-by: Ziqi Fan <ziqif@nvidia.com>
 2025-11-21 16:49:20 -08:00
Keiven C 75bf7c9b0f
fix: expose LMCache metrics via Dynamo metrics endpoint (#4461) 
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
 2025-11-19 21:09:13 -08:00
ishandhanani 48c340f430
fix: point to new sglang container and rm references to old (#4383) 2025-11-18 07:26:55 +00:00
Indrajit Bhosale c3984bc2d7
fix: Move trtllm multimodal worker to use ModelInput.Token (#4373) 
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
 2025-11-18 05:05:09 +00:00
Ben Hamm 88dfd1b338
docs: Clean up incomplete recipes and clarify Kubernetes-only focus (#4159) 
Signed-off-by: Ben Hamm <ben.hamm@gmail.com>
Signed-off-by: Tanmay Verma <tanmay2592@gmail.com>
Signed-off-by: atchernych <atchernych@nvidia.com>
Co-authored-by: Biswa Panda <biswa.panda@gmail.com>
Co-authored-by: tanmayv25 <tanmay2592@gmail.com>
Co-authored-by: Tanmay Verma <tanmayv@nvidia.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>
Co-authored-by: atchernych <atchernych@nvidia.com>
 2025-11-18 02:13:48 +00:00
Kris Hung 1e120ed049
docs: Update vllm multimodal EPD doc (#4352) 2025-11-15 00:39:21 -08:00
Yan Ru Pei 2fc57eb10d
docs: update vllm mermaid diagram (#4320) 
Signed-off-by: PeaBrane <yanrpei@gmail.com>
 2025-11-13 22:43:32 +00:00
Keiven C 381c428c11
refactor: change TensorRT-LLM metrics prefix from trtllm: to trtllm_ (#4269) 
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
 2025-11-13 09:44:37 -08:00
Keiven C f817c59576
docs: reorganize prometheus.md to be consistent with docs/observability/metrics.md (#4262) 
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
 2025-11-12 18:51:18 -08:00
Keiven C 6bccf099f8
feat: deprecate DYN_SYSTEM_ENABLED in favor of DYN_SYSTEM_PORT (#4082) 
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
 2025-11-07 15:31:51 -08:00
Yan Ru Pei 9fa8125cc8
chore: trtllm use unified frontend (#4097) 
Signed-off-by: PeaBrane <yanrpei@gmail.com>
 2025-11-05 06:33:22 +00:00