v0.1.12
What's Changed
- chore: openapi update router by @Cifko in #516
- feat: refactor router logic by @jorgeantonio21 in #518
- feat: updated logic for stack get and update operation, fully atomic by @jorgeantonio21 in #519
- feat: handles cases where stream is drop by client by @jorgeantonio21 in #521
- feat: add instrument errors by @jorgeantonio21 in #523
- feat: handle concurrency request counter in a single atomic logical flow by @jorgeantonio21 in #525
- feat: change order of middleware by @jorgeantonio21 in #530
- chore: add more connection libp2p logs by @maschad in #532
- ci: add Sui related security alerts to audit ignore by @maschad in #531
- chore(deps): bump blake3 from 1.7.0 to 1.8.0 by @dependabot in #527
- chore(deps): bump clap from 4.5.32 to 4.5.34 by @dependabot in #528
- chore(deps): bump once_cell from 1.21.1 to 1.21.3 by @dependabot in #529
- feat: handle unavailable stacks as non locked by @jorgeantonio21 in #535
- feat: reswap middleware by @jorgeantonio21 in #537
- build: allow for non-nvidia runtime builds by @maschad in #539
- feat: handle streamer synchronization for proxy and node by @jorgeantonio21 in #540
- ci: updated security advisories by @maschad in #549
- chore(deps): bump flate2 from 1.1.0 to 1.1.1 by @dependabot in #545
- chore(deps): bump blake3 from 1.8.0 to 1.8.1 by @dependabot in #547
- chore(deps): bump clap from 4.5.34 to 4.5.35 by @dependabot in #548
- feat: add confidential and non-confidential latency metrics by @maschad in #557
- feat: openrouter integration by @jorgeantonio21 in #543
- feat: update contract info by @jorgeantonio21 in #562
- deps: upgrade crossbeam-channel due to advisory by @maschad in #566
- chore(deps): bump sqlx from 0.8.3 to 0.8.4 by @dependabot in #565
- chore(deps): bump anyhow from 1.0.97 to 1.0.98 by @dependabot in #563
- chore(deps): bump clap from 4.5.35 to 4.5.36 by @dependabot in #564
- feat: update sui crates by @jorgeantonio21 in #568
- chore(deps): bump nvml-wrapper from
7552dacto0d41643by @dependabot in #573 - chore(deps): bump blake3 from 1.8.1 to 1.8.2 by @dependabot in #569
- chore(deps): bump clap from 4.5.36 to 4.5.37 by @dependabot in #570
- build: changes needed for testground e2e test by @maschad in #567
- feat: add heartbeat service by @maschad in #574
- feat: lock the concurrent request counter #579 by @Cifko in #580
- feat: add middleware metrics by @Cifko in #576
- feat: check failed status of streamer by @jorgeantonio21 in #582
- fix: 0 concurrent requests by @Cifko in #583
- fix: concurrent release lock too soon by @Cifko in #584
- chore: integrate Sentry SDK by @maschad in #577
- feat: add nvswitch remote attestation generation for multi-gpu ppcie setups by @jorgeantonio21 in #575
- chore: polluted logs by @Cifko in #585
- feat: revert concurrent access block and allow for failing txs by @jorgeantonio21 in #587
- feat: update prometheus url by @jorgeantonio21 in #588
- feat: review prometheus vllm metrics by @jorgeantonio21 in #589
- fix: propagate too many requests to proxy by @Cifko in #590
- feat: change prometheus url by @jorgeantonio21 in #591
- feat: join metric queries for prometheus into one by @Cifko in #595
- fix: get_metrics job url order by @Cifko in #596
- fix: update message returned for too many requests by @maschad in #597
- fix: add prom metrics querying to background tasks by @maschad in #598
- chore: update too many requests code by @maschad in #599
- chore(deps): bump chrono from 0.4.40 to 0.4.41 by @dependabot in #601
- chore(deps): bump sha2 from 0.10.8 to 0.10.9 by @dependabot in #602
- chore(deps): bump axum from 0.8.3 to 0.8.4 by @dependabot in #603
- build: fix build by @maschad in #606
- fix: optimize prom querying for vllm instances by @maschad in #605
- fix: Remove unused
total_hashcolumn by @maschad in #609 - feat: add node exporter for observability by @maschad in #608
- feat: handle completions endpoint by @jorgeantonio21 in #611
- build: add log collection for vllm instances by @maschad in #612
- chore(deps): bump tower-http from 0.6.2 to 0.6.4 by @dependabot in #614
- chore(deps): bump clap from 4.5.37 to 4.5.38 by @dependabot in #615
- chore(deps): bump tempfile from 3.19.1 to 3.20.0 by @dependabot in #616
- chore: update openapi.yml by @Cifko in #617
- chore: attempt to parse error messages by @maschad in #613
- feat: integrate develop branch by @maschad in #607
- chore(deps): bump utoipa-swagger-ui from 9.0.1 to 9.0.2 by @dependabot in #626
- chore(deps): bump tokio from 1.45.0 to 1.45.1 by @dependabot in #627
- chore(deps): bump sqlx from 0.8.5 to 0.8.6 by @dependabot in #628
- fix: completions estimations not triggered by @Cifko in #634
- feat: merge develop into main branch by @jorgeantonio21 in #629
Full Changelog: v0.1.11...v0.1.12