Repository navigation
perf(voice): make _TTS_PIPELINE_DEPTH env-configurable; default 2 (#6811) - #6812
Merged
Merged
Conversation
) Pocket TTS calls run via run_in_executor and serialize on the GIL/model lock — depth>2 only adds queue contention without true parallelism. Lowering default from 3 to 2 keeps one chunk synthesizing ahead while the client plays the previous chunk (the actual jitter-absorption goal of #6752) without piling up backlog. AUTOBOT_TTS_PIPELINE_DEPTH overrides the default, clamped to 1..8 to prevent ops typos OOMing the worker. Invalid values log a warning and fall back to 2. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Contributor
|
| Metric | Count |
|---|---|
| Total Violations | 1 |
| SSOT Violations (high priority) | 1 |
| Other Violations | 0 |
⚠️ 1 values have SSOT config equivalents!
These should be replaced with SSOT config imports:
Python:
from src.config.ssot_config import config
# Use: config.vm.main, config.port.backend, config.backend_urlTypeScript:
import config from '@/config/ssot-config'
// Use: config.vm.main, config.port.backend, config.backendUrl📖 See SSOT_CONFIG_GUIDE.md for documentation.
4 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
_TTS_PIPELINE_DEPTHwas hardcoded to 3 (#6752). Pocket TTS calls run vialoop.run_in_executor(None, _run_synthesis, ...)and serialize on the GIL/model lock — depth>2 only adds queue contention without true parallelism.This PR:
AUTOBOT_TTS_PIPELINE_DEPTHenv var overrideVerification
Edge cases tested:
python -m py_compilepasses.Test plan
depth=3AUTOBOT_TTS_PIPELINE_DEPTH=1(sequential) and=4(over-saturated) in dev to compareInvalid AUTOBOT_TTS_PIPELINE_DEPTH=...on bad valueCloses
Closes #6811
Related: #6810 (single-WS unification), #6752 (original jitter-absorption introducing depth=3)