Commit History
2 days ago
-
litertlm_manifest.json: the externalized file's sha256, size and sections; min runtime 0.19.0 and the Android GPU known issue (LiteRT-LM#3986)
Verified signature1e5fdc4 -
Move the externalized file from the web branch to main (TFLiteWeights sections; Android GPU needs LiteRT-LM 0.19.0 or later)
Verified signature0cb76df
7 days ago
-
Add known runtime issues: the second-turn stop token and the final mark before LiteRT-LM 0.17.0
Verified signatureAdds the lines under Known runtime issues; nothing else in the card changes.7840209
12 days ago
-
Say that the CLI's Init counts engine creation twice (LiteRT-LM #4057)
Verified signatureThe CLI's printed Init includes both Init Total and the phases inside it. One sentence, no number changed.2bdadb1
25 days ago
-
manifest 0.1.3: capabilities.thinking.control = never (what the bundle's template does about thinking, derived from the template inside the bundle)
Verified signature7b21064
-
Card: measured device / browser results (edge-compat, 2026-09)
Verified signatureddb8ab6
-
card: Galaxy S26 same-handset GPU/CPU speed pair (2026-09-05 CPU control) replaces 'no speed rows'; Android recommendation is cpu, as in litertlm_manifest.json
Verified signaturefbacbc7 -
Card: definition line (LiteRT, 2026-09)
Verified signaturec540353
-
manifest: same-device CPU control rows on the Galaxy S26 for the flagship GPU recommendation (S7 backfill 2026-09-05); the recommendation is rewritten from the measured pair (measured win, kept for prefill, or reversed to cpu)
Verified signature51105ef
-
Add litertlm_manifest.json (deployment manifest 0.1.2: variant selection, verified backends, Android/Apple recommendations, measured rows with conditions)
Verified signaturecc8f2d3 -
Card: base_model_relation: quantized (list under the base model's Quantizations)
Verified signature9b3eff1
-
Add measured Raspberry Pi 5 (CPU) section
Verified signatureNumbers from the 2026-09 Raspberry Pi 5 LLM sweep: litert-lm benchmark 0.16.1, CPU backend, 4 threads, 256 prefill + 256 decode tokens, compile cache disabled, 3 invocations per file with cooldown, thermal throttle state verified 0x0 on every run, and a real-generation gate on the same backend before any number was recorded. Median + spread, never single-shot.b49ee56
-
Add measured Galaxy S26 GPU backend section
Verified signatureFunctional verdict from the S26 GPU gate. Primary log: litertlm-convert/community_accel_work/s4_gpu_gate/results.jsonl. Delegation counts and peak RSS are read from that run's own log; throughput is deliberately absent, because an Android GPU speed is not quotable without a CPU row from the same phone and that control has not been run.75fd18f
-
card: note the 3B sibling and that the two are not benchmarked against each other
Verified signaturec4c83fe -
Qwen2.5-Coder-1.5B-Instruct int4 (blockwise-32 + OCTAV, externalised embedder)
Verified signature6fbe02e -
Qwen2.5-Coder-1.5B-Instruct LiteRT-LM card
Verified signatureb4e1811 -
initial commit
Verified signature758bb1d