Commit Graph

  • a2a37c0ebe discovery fixed Gelu Vrabie 2025-08-15 15:23:20 +01:00
  • 57073f35c3 collection of fixes for Shanghai demo Gelu Vrabie 2025-08-15 15:21:51 +01:00
  • 7e19804aa5 Integrate flake parts Andrei Cravtov 2025-08-13 11:55:22 +03:00
  • dbcd09aa53 No 70b Matt Beton 2025-08-12 18:42:27 +01:00
  • c1d5b381f4 70B model unit test only runs if its downloaded Matt Beton 2025-08-07 10:41:56 +01:00
  • 473512ddd0 r1 size Alex Cheema 2025-08-04 22:57:31 +08:00
  • 817c5993f0 fix dem model cards yo Alex Cheema 2025-08-04 10:19:22 +08:00
  • 75ecda55a9 fix gitignore Gelu Vrabie 2025-08-04 13:49:49 +01:00
  • c560c55c4e build and release on staging Alex Cheema 2025-08-04 07:41:09 +08:00
  • f51f8f72f8 app launches python modules Sami Khan 2025-08-04 03:18:31 +05:00
  • 407796d18f Minor dashboard fixes Seth Howes 2025-08-04 06:15:01 +08:00
  • 6daf7f31f7 clean model cards Alex Cheema 2025-08-04 05:31:30 +08:00
  • f352ddfc5f run configure_mlx.sh in run.sh Alex Cheema 2025-08-04 03:59:42 +08:00
  • 6855a7727d set a 15 sec timeout for getting initial download progress Alex Cheema 2025-08-03 20:37:20 +08:00
  • 1fe4ed3442 Worker Exception & Timeout Refactor Matt Beton 2025-08-02 16:28:37 +01:00
  • 92c9688bf0 Remove rust Alex Cheema 2025-08-02 08:16:39 -07:00
  • a46f8c3cd1 app Sami Khan 2025-08-02 07:14:27 +05:00
  • 71bafabc63 Dashboard with instances Seth Howes 2025-08-01 14:38:07 +01:00
  • 0e32599e71 fix libp2p + other prs that were wrongly overwritten before (111,112,117,118,1119 + misc commits from Alex) Gelu Vrabie 2025-07-31 20:36:47 +01:00
  • 2031d9481d fix api get_state Alex Cheema 2025-07-30 07:15:15 -07:00
  • b350ededb2 Test Supervisor Errors. Matt Beton 2025-07-30 13:30:54 +01:00
  • ff3d11c748 just run Gelu Vrabie 2025-07-29 16:58:27 +01:00
  • 25fa46c6f6 Update CODEOWNERS Gelu Vrabie 2025-07-29 13:08:29 +01:00
  • 3f192f20cc Reinstate dashboard Seth Howes 2025-07-28 15:18:23 -07:00
  • a2b4093d25 add metrics: gpu_usage, temp, sys_power, pcpu_usage, ecpu_usage, ane_… Alex Cheema 2025-07-28 23:02:33 +01:00
  • 12566865d5 better profiling Alex Cheema 2025-07-28 22:15:04 +01:00
  • b88abf1cc2 fix topology disconnects and add heartbeat Gelu Vrabie 2025-07-28 22:00:05 +01:00
  • dbd0bdc34b fix ci linter Alex Cheema 2025-07-28 20:12:48 +01:00
  • 20241e3290 some finishing touches to get this working e2e Alex Cheema 2025-07-28 13:07:29 +01:00
  • 176d077c87 Fix IPv4 serialisation for topology Seth Howes 2025-07-28 13:07:10 +01:00
  • c3c8ddbce8 fix forwarder supervisor tests Gelu Vrabie 2025-07-28 13:03:43 +01:00
  • 36a5d75efd Fix download tests Matt Beton 2025-07-28 12:51:10 +01:00
  • e9b803604b Add Multiaddr type and refactor Hosts type for creating shard placement Seth Howes 2025-07-28 11:39:46 +01:00
  • b285a9f0b7 fix placement tests Alex Cheema 2025-07-28 11:18:32 +01:00
  • 57ca487fde Fixes for running this end to end Alex Cheema 2025-07-28 10:51:03 +01:00
  • b687dec6b2 Discovery integration master Andrei Cravtov 2025-07-27 15:43:59 +03:00
  • 98f204d14a Fix placement single node Alex Cheema 2025-07-26 20:08:37 +01:00
  • 93330f0283 Inference Integration Test Matt Beton 2025-07-26 20:08:25 +01:00
  • 2e4635a8f5 add node started event Gelu Vrabie 2025-07-26 19:12:26 +01:00
  • 261e575262 Serialize topology Gelu Vrabie 2025-07-25 15:09:03 +01:00
  • a97fb27c64 Glue TWO Alex Cheema 2025-07-25 14:32:34 +01:00
  • 9be08ec7dd add resource monitor Gelu Vrabie 2025-07-25 13:10:53 +01:00
  • a241c92dd1 Glue Alex Cheema 2025-07-25 13:10:29 +01:00
  • 6f8e3419d5 Placement strategy Seth Howes 2025-07-24 20:22:40 +01:00
  • 4c0e4ef853 Go build Gelu Vrabie 2025-07-24 19:45:45 +01:00
  • f41531d945 Worker Loop Matt Beton 2025-07-24 18:44:31 +01:00
  • 67c70b22e4 Best master Alex Cheema 2025-07-24 17:12:52 +01:00
  • 3730160477 Fix the node-ID test Andrei Cravtov 2025-07-24 17:09:12 +01:00
  • df1fe3af26 Topology apply Gelu Vrabie 2025-07-24 14:27:09 +01:00
  • 5097493a42 Fix tests Matt Beton 2025-07-24 13:22:58 +01:00
  • a6b3ab6332 Worker plan Alex Cheema 2025-07-24 12:45:27 +01:00
  • 56d3565781 Add apply functions Gelu Vrabie 2025-07-24 11:02:20 +01:00
  • 3ab5609289 wrote race-condition-free persistent NodeID-getting function Andrei Cravtov 2025-07-23 20:18:56 +01:00
  • 7a452c3351 Fix tests Matt Beton 2025-07-23 18:25:50 +01:00
  • 7ac23ce96b Refactor tasks / commands / api Seth Howes 2025-07-23 15:52:29 +01:00
  • 81060b7062 Made basedpyright work with Jetbrains environment Andrei Cravtov 2025-07-23 14:12:11 +01:00
  • 8d2536d926 Implemented basic discovery library in Rust + python bindings Andrei Cravtov 2025-07-23 13:11:29 +01:00
  • 76f903504c fix Gelu Vrabie 2025-07-22 22:29:35 +01:00
  • cd9a1a9192 Topology update Seth Howes 2025-07-22 22:29:17 +01:00
  • 14b3c4a6be New API! Matt Beton 2025-07-22 21:21:12 +01:00
  • 596d9fc9d0 add forwarder service Gelu Vrabie 2025-07-22 20:53:26 +01:00
  • 53c652c307 Fix tests! Matt Beton 2025-07-22 15:20:32 +01:00
  • 5adad08e09 New events Matt Beton 2025-07-22 15:16:06 +01:00
  • 108128b620 fix sqlite connector Gelu Vrabie 2025-07-21 22:43:09 +01:00
  • 449fdac27a Downloads Alex Cheema 2025-07-21 22:42:37 +01:00
  • cb101e3d24 Refactor model types Seth Howes 2025-07-21 20:35:27 +01:00
  • 54efd01d77 add forwarder supervisor Gelu Vrabie 2025-07-21 20:21:43 +01:00
  • bae58dd368 Refactor worker + master state into single state Seth Howes 2025-07-21 19:36:54 +01:00
  • d19aa4f95a Simplify Task type + merge control & data plane types into single type Seth Howes 2025-07-21 17:10:09 +01:00
  • 2f64e30dd1 Add sqlite connector Gelu Vrabie 2025-07-21 14:10:29 +01:00
  • bb7f1ae994 New worker Alex Cheema 2025-07-18 10:08:56 +01:00
  • cc45c7e9b9 Fixed events issue. Matt Beton 2025-07-17 12:21:01 +01:00
  • 038cc4cdfa fix: Normalize Naming Arbion Halili 2025-07-16 16:11:51 +01:00
  • e2a7935019 fix: Fix incorrect logic Arbion Halili 2025-07-16 14:39:20 +01:00
  • 6a671908a3 fix: FrozenSet Related Bits Arbion Halili 2025-07-16 13:45:57 +01:00
  • 520b1122a3 fix: Many Fixes Arbion Halili 2025-07-16 13:35:31 +01:00
  • d9b9aa7ad2 Merge branch 'master-node' into staging Arbion Halili 2025-07-15 16:32:08 +01:00
  • 7fa7de8e83 more incomplete trash Arbion Halili 2025-07-15 13:40:21 +01:00
  • 9f96b6791f fix: Some, still broken Arbion Halili 2025-07-15 12:58:50 +01:00
  • 9b3c105bea fix: Save Andrei's sanity Arbion Halili 2025-07-15 12:30:46 +01:00
  • 8060120136 tweak Arbion Halili 2025-07-14 22:37:53 +01:00
  • df6626fa31 fix: Event definitions, state definitions Arbion Halili 2025-07-14 21:41:14 +01:00
  • 70f0f09c05 Tweaked, Still Broken tho Arbion Halili 2025-07-14 21:19:39 +01:00
  • 8799c288b0 BROKEN: work thus far Arbion Halili 2025-07-14 21:09:08 +01:00
  • 4e4dbf52ec fix: Use Nix-compatible LSP set-up Arbion Halili 2025-07-14 21:08:43 +01:00
  • 21acd3794a New Runner! Matt Beton 2025-07-10 16:34:35 +01:00
  • b0bd951005 Merge Basic Interfaces Arbion Halili 2025-07-09 19:04:21 +01:00
  • 74d56e52ff fix: Improve naming Arbion Halili 2025-07-07 20:22:27 +01:00
  • fe17aaf9f8 fix: Make master hold a queue of task data Arbion Halili 2025-07-07 20:22:00 +01:00
  • e1894bc106 refactor: A Lot Arbion Halili 2025-07-07 20:19:08 +01:00
  • 81cf6bce64 refactor: Simplify networking Arbion Halili 2025-07-07 19:32:21 +01:00
  • 6c8b8b30ae added rust to flake Andrei Cravtov 2025-07-07 18:11:40 +01:00
  • 0425422f55 Simple fix Matt Beton 2025-07-07 17:18:43 +01:00
  • 03a1cf59a6 Matt's interfaces Matt Beton 2025-07-07 16:42:52 +01:00
  • 367e76c8fa fix: Fix validation over Task types Arbion Halili 2025-07-04 17:25:14 +01:00
  • cda3de2a28 fix: Use state for tasks Arbion Halili 2025-07-04 15:08:54 +01:00
  • 10224d09de refactor: Distinguish the topology of the control plane from that of the data plane Arbion Halili 2025-07-03 15:45:54 +01:00
  • c456934342 refactor: Remove timestamp from Wrapped Events Arbion Halili 2025-07-03 13:05:35 +01:00
  • 0b6aadf576 refactor: Add safe state mutation method .apply() Arbion Halili 2025-07-03 12:33:29 +01:00
  • f8039e20e0 feature: Add pretty_name to ModelMetadata Arbion Halili 2025-07-03 12:32:32 +01:00