Commit History
Yesterday
-
Card: add a note on litert-lm's 10-minute send_message timeout
Verified signaturec0d6ee9
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 signatured3b033c -
Move the externalized file from the web branch to main (TFLiteWeights sections; Android GPU needs LiteRT-LM 0.19.0 or later)
Verified signature597b47e
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.c024210
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.9493a41
25 days ago
-
manifest 0.1.3: capabilities.thinking.control = model (what the bundle's template does about thinking, derived from the template inside the bundle)
Verified signature90dc72b
26 days ago
-
Card: measured device / browser results (edge-compat, 2026-09)
Verified signature74a5c21
27 days ago
-
GPU graph re-ship: KV-cache update and attention rewritten into the runtime's GPU composite ops plus a 16-token prefill signature; weights, tokenizer and metadata byte-identical; CPU output bit-identical (card and manifest updated)
Verified signature1c9be2e
-
Card: measured device / browser results (edge-compat, 2026-09)
Verified signature96991f3 -
Card: compatibility line (edge-compat, 2026-09)
Verified signature8980f56
-
Card: definition line (LiteRT, 2026-09)
Verified signature5b756a5
-
manifest: Galaxy S26 GPU rows from the S4 gate sweep (Android recommendation where none existed)
Verified signatureef921ab -
Card: base_model_relation: quantized (list under the base model's Quantizations)
Verified signature56874e2
-
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.6e57ddd
-
Manifest: regenerate after the thought-channel re-pack (sha256 + capabilities.thinking)
Verified signature33d43e2 -
Card: note the thought-channel declaration (metadata only, weights unchanged)
Verified signature2a20068 -
Declare the thought channel so the reasoning is separable and the thinking budget applies (metadata only; weights byte-identical)
Verified signature534513d
-
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.4ca77d5
-
Add litertlm_manifest.json — machine-readable deployment manifest (variant selection, backend recommendations, measured performance)
Verified signaturec2a4bca
-
Card: measured Performance table (M4 Max CPU/GPU + on-device where measured), accuracy note
Verified signaturec7dc6d7
-
docs: add Training data & PII section (submission-guideline compliance)
Verified signatureab1a8fa
-
Upload folder using huggingface_hub
Verified signature384e95e -
initial commit
Verified signatured50cf37