Add native Windows CPU Qwen TTS Omni stage and profile evidence
This commit is contained in:
1 parent
8569995591
commit
bb8735effc
24 files changed
+25090
-14
No files matched your search
@@ -5,7 +5,9 @@ per request, with a fixed input bucket and copied host tensors. A second backend
|
||||
`external.llamacpp.text.v1`, owns one pinned GGUF whole-model server process and
|
||||
returns complete text requests. `external.crisp.tts.v1` owns a pinned
|
||||
CustomVoice GGUF talker, codec and local hybrid CPU+Radeon process, returning
|
||||
complete PCM audio. All use the normal `Omni` / `AsyncOmni` APIs,
|
||||
complete PCM audio. `external.qwen_tts.cpu.v1` owns the original BF16 CustomVoice
|
||||
checkpoint in an isolated native Windows CPU process and also returns complete
|
||||
PCM audio. All use the normal `Omni` / `AsyncOmni` APIs,
|
||||
`PipelineConfig`, `StageRuntime`, `StagePool` and orchestrator. Native vLLM stages
|
||||
retain their model execution, KV cache, sampling and batching. No accelerator is
|
||||
mandatory. The llama.cpp backend currently uses the complete-request graph
|
||||
@@ -13,7 +15,9 @@ control path for admission and acknowledgement; it is not an ONNX graph and does
|
||||
not yet support incremental token events or restart after active cancellation.
|
||||
The CrispASR route likewise lacks playable incremental PCM and post-cancel
|
||||
restart; its current placement gate is specific to the measured HX370 Radeon
|
||||
890M shared-RAM configuration.
|
||||
890M shared-RAM configuration. The Qwen CPU route likewise returns a terminal
|
||||
WAV only; its worker pins an isolated Transformers 4.57.3 overlay and verifies
|
||||
CPU placement and weight hashes before serving.
|
||||
|
||||
## Boundaries
|
||||
|
||||
@@ -64,6 +68,8 @@ This section preserves the 2026-09-22 audit. For the latest per-cell disposition
|
||||
|
||||
The [Qwen3-TTS CPU+Radeon whole-session path](../../benchmarks/edge_harness/results/e2e_expansion_20260923/evidence/qwen_tts_omni_hybrid/README.md) also completed two named text-to-audio inputs and 20 serial Omni requests with exact PCM parity to its standalone record. It verifies pinned executable and weights, logged hybrid placement, one-slot shared-RAM admission, terminal audio and cancellation drain. Playable streaming, post-cancel restart, loading/iGPU peaks, sustained use and broader speech quality remain open; RTF still exceeds 1. No joint CPU+iGPU+NPU claim follows from this result.
|
||||
|
||||
The [native Windows CPU Qwen3-TTS Omni path](../../benchmarks/edge_harness/results/e2e_expansion_20260923/evidence/qwen_tts_omni_cpu/README.md) completed two named text-to-WAV inputs and 20 serial Omni requests with exact PCM parity to the standalone PyTorch record. It verifies pinned weights, CPU-only placement, a 10 GiB host reservation, a 4 GiB pre-load refusal, terminal audio and cancellation drain. Request-wall p50/p95 were 15.32/15.60 s for 4.56 s of audio. Playable streaming, post-cancel restart, loading peak, broad voice quality and sustained use remain open. This CPU route does not qualify AMD or mobile execution.
|
||||
|
||||
**All 60 named pairings were checked on 2026-09-22** through actual runs,
|
||||
raw-record review or artifact/runtime preflight. This is not 60 successful
|
||||
executions. Each cell links to its evidence, finding and next required step.
|
||||
|
||||
Reference in new issue
Block a user