tzhouamandClaude Fable 5.1 c893b638ad [Edge][WP5] Accumulate per-step codec delta rows (DELTA mode delivers only the newest row) ...

Measured after the DELTA fix: 53 engine outputs for 52 rows, but the client
still received everything at once because each per-step payload is the newest
row only and the row alignment treated it as a cumulative snapshot (one yield
at the first row, one at the end). accumulate_codec_rows folds delta rows and
the final consolidated matrix into one growing matrix; unit test drives the
generator with per-step deltas and asserts one yield per step.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

2026-09-09 16:45:24 +08:00

..

duplex

[Core] Graduate MiniCPM-o 4.5 and PersonaPlex full-duplex serving out of experimental (#6196)

2026-09-05 08:20:21 +00:00

openai

[Core] Graduate MiniCPM-o 4.5 and PersonaPlex full-duplex serving out of experimental (#6196)

2026-09-05 08:20:21 +00:00

openai_api

[Edge][WP5] Accumulate per-step codec delta rows (DELTA mode delivers only the newest row)

2026-09-09 16:45:24 +08:00

test_async_omni_diffusion_config.py

[diffusion][feature] Add component-selective offload policies (#5929)

2026-09-06 05:40:09 +08:00

test_async_omni_duplex.py

[Core] Graduate MiniCPM-o 4.5 and PersonaPlex full-duplex serving out of experimental (#6196)

2026-09-05 08:20:21 +00:00

test_async_omni_pause_sleep_routing.py

[Bugfix] Fix colocate-async sleep admission race and deliver AR abort tokens (#6367)

2026-08-29 09:11:39 +00:00

test_async_omni_prompt_update.py

[Frontend] Add midway prompt update for streaming video generation (#4652)

2026-07-27 14:07:43 +08:00

test_async_omni.py

[Bugfix] Fix colocate-async sleep admission race and deliver AR abort tokens (#6367)

2026-08-29 09:11:39 +00:00

test_duplex_fence_propagation.py

[Core] Graduate MiniCPM-o 4.5 and PersonaPlex full-duplex serving out of experimental (#6196)

2026-09-05 08:20:21 +00:00

test_omni_base_profiler.py

[Config] Remove diffusion_batch_size and use max_num_seqs instead. (#6484)

2026-09-01 01:02:54 +00:00

test_omni_entrypoints.py

text and image metric (#6150)

2026-08-26 02:54:45 +00:00

test_omni_new_request_data.py

[Refactor][1/N Scheduler]Remove duplicated AR/generation scheduler plumbing and establish explicit shared lifecycle contracts. (#5461)

2026-08-04 15:10:47 +08:00

test_omni_sleep_mode.py

[Bugfix] Fix colocate-async sleep admission race and deliver AR abort tokens (#6367)

2026-08-29 09:11:39 +00:00

test_omni_snapshot_download.py

[Rebase] Rebase to vllm 0.28.0 (#6606)

2026-08-27 06:12:55 +00:00

test_pd_disaggregation.py

[Refactor][CI] Reorganize test tree, and move slow e2e to weekly (#4951)

2026-07-29 23:53:03 +08:00

test_realtime_connection_helpers.py

[Feature]Support audio streaming input and output-phase2 (#2581)

2026-04-18 15:42:41 +08:00

test_resolve_dreamzero_config.py

[Model] Add LTX-2.5 support (#6070)

2026-08-15 18:27:23 +08:00

test_serve.py

[Model] FP8 Support For Boogu-Image (#6925)

2026-09-06 04:48:38 +00:00

test_stage_utils.py

[Bugfix] Fix colocate-async sleep admission race and deliver AR abort tokens (#6367)

2026-08-29 09:11:39 +00:00

test_stream_finish_reason.py

[Bugfix] Preserve prompt token usage details (#5181)

2026-08-20 20:05:05 +00:00

test_utils.py

[Bugfix] Validate --stage-overrides shape in parse_stage_overrides (drop field allowlist) (#6230)

2026-09-02 23:19:08 -07:00