Skip to content

Actions: mlcommons/endpoints

Actions

Auto Request Review

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
auto-review.yml
364 workflow runs
364 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
docs(edge-agentic): add BFCL v4 quantization calibration dataset Auto Request Review #290: Pull request #424 opened by Palanivelg
9s Palanivelg:edge-agentic-calibration-dataset
Palanivelg:edge-agentic-calibration-dataset
9s
refactor(metrics): unify the percentile convention; address #417 round-3 review Auto Request Review #289: Pull request #423 opened by nvzhihanj
7s refactor/es-percentile-unification
refactor/es-percentile-unification
7s
feat: report OpenAI finish reason distribution Auto Request Review #288: Pull request #422 ready_for_review by hvagadia
9s hvagadia:agent/finish-reason-reporting
hvagadia:agent/finish-reason-reporting
9s
feat: report OpenAI finish reason distribution Auto Request Review #287: Pull request #422 opened by hvagadia
11s hvagadia:agent/finish-reason-reporting
hvagadia:agent/finish-reason-reporting
11s
feat(metrics): opt-in MLPerf early-stopping percentile estimates (LoadGen parity) Auto Request Review #286: Pull request #417 ready_for_review by nvzhihanj
8s feat/early-stopping-percentile-estimate
feat/early-stopping-percentile-estimate
8s
feat(metrics): opt-in MLPerf early-stopping percentile estimates (LoadGen parity) Auto Request Review #285: Pull request #417 ready_for_review by nvzhihanj
9s feat/early-stopping-percentile-estimate
feat/early-stopping-percentile-estimate
9s
refactor(benchmark): split execute.py into execute/profiling/accuracy/pipeline Auto Request Review #284: Pull request #421 opened by arekay-nv
12s refactor/execute-split
refactor/execute-split
12s
feat(metrics): opt-in MLPerf early-stopping percentile estimates (LoadGen parity) Auto Request Review #283: Pull request #417 opened by nvzhihanj
10s feat/early-stopping-percentile-estimate
feat/early-stopping-percentile-estimate
10s
DO_NOT_MERGE : Cherry-pick PR403 Auto Request Review #282: Pull request #415 opened by arekay-nv
10s arekay/cherry_pick_pr403
arekay/cherry_pick_pr403
10s
feat: optional VBench (WAN 2.2) accuracy scorer in Dockerfile.dev (PROVISION_VBENCH) Auto Request Review #281: Pull request #414 opened by wu6u3tw
9s wu6u3tw:feat/dockerfile-optional-vbench
wu6u3tw:feat/dockerfile-optional-vbench
9s
fix: reasoning forwarding Auto Request Review #280: Pull request #413 opened by tianmu-li
8s tianmu-li:fix/reasoning_forwarding
tianmu-li:fix/reasoning_forwarding
8s
Add License Scanning and Reporting for Endpoints Changes on Main. Auto Request Review #279: Pull request #412 opened by arav-agarwal2
11s feat/add-scanoss-license-checking
feat/add-scanoss-license-checking
11s
fix(client): pace connection establishment; auto warmup claims 25% of the port budget Auto Request Review #278: Pull request #411 opened by viraatc
8s fix/paced-warmup-auto-budget
fix/paced-warmup-auto-budget
8s
feat(config): consolidate all time knobs into settings.timeouts; make --timeout a real run watchdog Auto Request Review #277: Pull request #409 opened by viraatc
13s timeouts-consolidation
timeouts-consolidation
13s
fix(deps): clear pillow/click pip-audit CVEs Auto Request Review #276: Pull request #408 opened by arekay-nv
9s fix/deps-pillow-click-cve
fix/deps-pillow-click-cve
9s
fix: reserve ephemeral-port headroom for the auto max-connections default Auto Request Review #275: Pull request #407 opened by nvzhihanj
8s fix/auto-max-connections-port-headroom
fix/auto-max-connections-port-headroom
8s
fix: Salt failure is a hard error Auto Request Review #274: Pull request #406 opened by arekay-nv
8s arekay/salt_failure_hard_error
arekay/salt_failure_hard_error
8s
feat :Testing workflow to push images Auto Request Review #273: Pull request #405 opened by arekay-nv
8s arekay/push_image_workflow
arekay/push_image_workflow
8s
fix(endpoint-client): retry pre-response connection resets (opt-in) Auto Request Review #272: Pull request #404 opened by Palanivelg
9s Palanivelg:feat/transport-retry-pre-response-reset
Palanivelg:feat/transport-retry-pre-response-reset
9s
feat: run wan2.2 VBench accuracy from the prebuilt image — bake scorer in + fix cold-start failures Auto Request Review #271: Pull request #403 opened by wu6u3tw
6s wu6u3tw:wan22-vbench-deps
wu6u3tw:wan22-vbench-deps
6s
feat(metrics): consolidate gpt-oss/deepseek accuracy, dedup reporting, surface TPS Auto Request Review #270: Pull request #400 opened by arekay-nv
10s arekay/feat-consolidate-accuracy-reporting
arekay/feat-consolidate-accuracy-reporting
10s
feat(report): record run_config (seeds + load/warmup) in result_summary.json Auto Request Review #269: Pull request #377 ready_for_review by nvzhihanj
9s fix/report-fieldorder-gitsha
fix/report-fieldorder-gitsha
9s
fix: use cwd for reported sha Auto Request Review #268: Pull request #398 opened by arekay-nv
8s arekay/fix_git_sha
arekay/fix_git_sha
8s
feat(config): add v6.1 ruleset and pin RNG seeds from submission ruleset Auto Request Review #267: Pull request #389 opened by arekay-nv
7s feat/random-seeds
feat/random-seeds
7s
feat: Enable per dataset max-osl Auto Request Review #266: Pull request #344 ready_for_review by arekay-nv
7s arekay/per_dataset_maxosl
arekay/per_dataset_maxosl
7s