tzhouamandClaude Fable 5.1 602e39647e [Edge][WP2] Finalize edge profile init knobs from init_profile; WP4 CPU emulation results ...

init_profile 20260909-112200 (1.7B, L20X, warm): default 152.0 s, eager_stage1
149.9 s, eager_both 110.9 s (first TTFA 15 s, no graphs), parallel_stage_init
94.6 s, edge 145.7 s. Edge profile now carries `orchestrator: parallel_stage_init:
true`, applied by the deploy_profile selector (explicit values win); graphs stay on.

hw_emulation 20260909-110229 (CPU venv, 0.6B, deploy_profile=auto):
x86_cpu_avx2 (4c, fp32) TTFA 2.65 s RTF 11.9; x86_cpu_avx512 (8c) TTFA 0.68 s
RTF 2.45; x86_cpu_amx (16c) TTFA 0.51 s RTF 1.72; arm64 logic-only same as avx2.
Emulation rows now record the auto-detected hardware class.

Adds tests/e2e/offline_inference/test_qwen3_tts_edge_profile.py (L3, one GPU).

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

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

..

accuracy

[Feat] Add support and testcase for HunyuanImage-3.0-Instruct-Distil (#4048)

2026-09-03 02:43:13 +00:00

features

[Feature] Define the runner preprocess phase contract and regression coverage (#7136)

2026-09-06 17:20:04 +00:00

offline_inference

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

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

online_serving

[Edge][WP5] Add codec-token streaming mode with on-device decoding

2026-09-09 11:10:13 +08:00

__init__.py

[ROCm] [CI] Add ROCm Dockerfile and AMD CI (vllm v0.12.0) (#280)

2025-12-21 11:51:37 +08:00