-
84ffeca8f2
fix(tts): add /health endpoint, fix language param for single-lang models
main
Billy D.
2026-02-22 12:19:06 -05:00
-
194a431e8c
feat(tts): add streaming SSE endpoint and sentence splitter
Billy D.
2026-02-22 10:45:58 -05:00
-
0fb325fa05
feat: FastAPI ingress for TTS — GET /api/tts returns raw WAV
Billy D.
2026-02-21 12:49:44 -05:00
-
59655e3dcf
feat: add SSE streaming support to LLM endpoint
Billy D.
2026-02-20 16:52:08 -05:00
-
a973768aee
fixing serve-llm stuff.
Billy D.
2026-02-18 07:30:00 -05:00
-
969e93cdd4
chore: trigger rebuild for new package registry
Billy D.
2026-02-17 08:30:02 -05:00
-
fd3234b79c
chore: trigger rebuild for new package registry
Billy D.
2026-02-17 08:29:35 -05:00
-
6f8b3241de
chore: add Renovate config for automated dependency updates
Billy D.
2026-02-13 15:34:08 -05:00
-
79dbaa6d2c
fix: add stop_token_ids and clamp max_tokens
Billy D.
2026-02-13 09:19:20 -05:00
-
96f7650b23
fix: respect VLLM_USE_TRITON_AWQ from runtime_env instead of hardcoding 0
Billy D.
2026-02-13 07:29:57 -05:00
-
f66de251eb
fix: add ENFORCE_EAGER env var to skip torch.compile on ROCm
Billy D.
2026-02-13 06:56:29 -05:00
-
6a391147a6
minor: refactoring big changes.
Billy D.
2026-02-12 18:47:50 -05:00
-
297b0d8ebd
fix: move mlflow import inside __init__ to avoid cloudpickle serialization failure
Billy D.
2026-02-12 07:06:49 -05:00
-
15e4b8afa3
fix: make mlflow_logger import optional with no-op fallback
Billy D.
2026-02-12 07:01:17 -05:00
-
7ec2107e0c
feat: add MLflow inference logging to all Ray Serve apps
Billy D.
2026-02-12 06:14:30 -05:00
-
2edafc33c0
async vllm is better.
Billy D.
2026-02-11 06:05:50 -05:00
-
c9d7a2b5b7
fixing coqui
Billy D.
2026-02-09 09:14:30 -05:00
-
4549295a07
trigger: test package upload after gitea temp fix
Billy D.
2026-02-03 20:12:30 -05:00
-
665416bb0e
chore: trigger build with repo secrets
Billy D.
2026-02-03 19:33:45 -05:00
-
e853b805ae
chore: trigger pipeline with org-level runner
Billy D.
2026-02-03 19:22:34 -05:00
-
9bc40cfd20
chore: trigger rebuild after gitea storage migration
Billy D.
2026-02-03 16:07:27 -05:00
-
4a560f9b9e
chore: retrigger pipeline after runner restart
Billy D.
2026-02-03 15:49:43 -05:00
-
baf86e5609
ci: semver based on commit message keywords
Billy D.
2026-02-03 15:25:15 -05:00
-
3fb6d8f9c2
chore: trigger rebuild after S3 storage migration
Billy D.
2026-02-03 15:12:54 -05:00
-
8ef914ec12
feat: initial ray-serve-apps PyPI package
Billy D.
2026-02-03 07:03:39 -05:00
-
eac8f27f2e
Initial commit
Billy Davies
2026-02-03 11:59:56 +00:00