tzhouamandClaude Fable 5.1 b22dabe270 [Edge][WP5] Keep DELTA outputs for talker-only (codec-token) deployments ...

The speech path forced FINAL_ONLY for Qwen3-TTS deployments without async
chunks, so a talker-only server emitted one engine output per request and all
codec frames arrived at once (measured: 1 engine output per request, first
codes at output #1). A talker-only stage (final_output + latent) now keeps
DELTA outputs so codec frames stream per step.

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

2026-09-09 16:21:31 +08:00

..

cli

[Edge][WP1] Add edge deploy profile and deploy_profile selector

2026-09-09 10:27:33 +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

[Edge][WP5] Keep DELTA outputs for talker-only (codec-token) deployments

2026-09-09 16:21:31 +08:00

openpi

[Core][Frontend] Support request-level batching for diffusion pipelines (#4079)

2026-06-29 18:09:19 +02:00

__init__.py

[Bug] Lazy-import entrypoints to fix subprocess pynvml crash (#2187)

2026-04-09 15:35:22 +08:00

async_omni.py

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

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

client_request_state.py

text and image metric (#6150)

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

duplex_request_client.py

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

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

omni_base.py

[Edge][WP2] Add initialization timeline and cold-start profiler

2026-09-09 11:01:39 +08:00

omni.py

text and image metric (#6150)

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

pd_utils.py

[Bugfix] Remove stale OmniStage import and type annotation (#3541)

2026-05-22 11:32:14 +08:00

stage_utils.py

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

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

utils.py

[Edge][WP2] Finalize edge profile init knobs from init_profile; WP4 CPU emulation results

2026-09-09 14:40:13 +08:00