anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

Track SA8775P InternVLA Cosmos encoder artifact

Browse Source
This commit is contained in:
tzhouam committed 2026-09-24 08:37:15 +08:00
1 parent 11c1a56467
commit 6af714cf9b
7 files changed
+63 -4
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/design/omni_edge_e2e_roadmap.md
+1 -1
View File
@@ -23,7 +23,7 @@ A separate [28-layer talker decode-step attempt](../../benchmarks/edge_harness/r
For M4, a [MiniCPM-o 4.5 speech-head study](../../benchmarks/edge_harness/results/e2e_expansion_20260924/evidence/minicpmo_tts_qualcomm/README.md) recovered the historical 20-layer ONNX source and matching S24/S25 fixtures. Both FP16 context-binary outputs preserved the ONNX CPU top-1 speech token on one decode step, with logits relative L2 0.346%/0.360%. Their 100-sample component profiles had p50/p95 8.537/9.006 ms and 7.197/7.615 ms, with all 1,029 execution-detail rows on NPU for each. New FP16 QNN DLC compiles passed for SA8775P, X Elite and RB3. SA8775P same-fixture NPU-requested inference preserved CPU top-1 speech token 1867 with 0.3568% logits relative L2 and 1.225% maximum K/V relative L2; placement profiling is pending. X Elite same-fixture inference also preserved token 1867 with 0.3170% logits relative L2; both placement profiles remain pending. RB3 FP16 QNN inference failed at graph load despite compile success; a TFLite CPU fallback compile passed with same-fixture CPU-requested inference pending. This is component C numerical evidence only, not thinker/encoder/vocoder or complete multimodal support.
For M4, a [Galaxy S25 Cosmos encoder attempt](../../benchmarks/edge_harness/results/e2e_expansion_20260924/evidence/internvla_cosmos_qualcomm/README.md) repackages the real Place_Markpen FP32 ONNX export after retaining two CPU parity fixtures. FLOAT16 QNN DLC inference returned a latent within 0.0524% relative L2 of the source on one synthetic pattern. Injecting that output into the real policy on local CPU changed synthetic actions by 0.742% relative L2, without a task tolerance. S25 six-frame component profile returned 100 samples at p50/p95 49.665/51.382 ms, with all 121 execution-detail rows on NPU; the action policy did not run on S25. The same encoder compiled to FP16 QNN DLC for X Elite CRD, with same-fixture NPU-requested inference pending. This is component/action-sensitivity evidence, not device-local M4 qualification.
For M4, a [Galaxy S25 Cosmos encoder attempt](../../benchmarks/edge_harness/results/e2e_expansion_20260924/evidence/internvla_cosmos_qualcomm/README.md) repackages the real Place_Markpen FP32 ONNX export after retaining two CPU parity fixtures. FLOAT16 QNN DLC inference returned a latent within 0.0524% relative L2 of the source on one synthetic pattern. Injecting that output into the real policy on local CPU changed synthetic actions by 0.742% relative L2, without a task tolerance. S25 six-frame component profile returned 100 samples at p50/p95 49.665/51.382 ms, with all 121 execution-detail rows on NPU; the action policy did not run on S25. The same encoder compiled to FP16 QNN DLC for X Elite CRD, with same-fixture NPU-requested inference pending; an SA8775P FP16 QNN DLC compile passed, with same-fixture NPU-requested inference pending. This is component/action-sensitivity evidence, not device-local M4 qualification.
The [WSL CPU expansion](../../benchmarks/edge_harness/results/e2e_expansion_20260923/README.md)
adds constrained three-stage MiniCPM-o text-to-speech requests and a CPU-only