Commit History
9 days ago
-
Add a known runtime issue: a preface with tools and no messages fails to render the chat template
Verified signatureAdds the lines under Known runtime issues; nothing else in the card changes.8f51599
21 days ago
-
Card: tool calls on litert-lm 0.18.0 — re-packed 2026-10-14 (llm_model_type qwen2p5, tool-result rendering and a JSON tool-call example in the chat template; metadata only); GPU executor defaults note
Verified signaturea1f7409 -
litertlm_manifest.json: Falcon-H1-3B-Instruct_int8.litertlm re-packed 2026-10-14 (llm_model_type qwen2p5, tool-result rendering and a JSON tool-call example in the chat template): new sha256 and LlmMetadata section size, the tool-call known_issues sentence and the GPU executor defaults sentence
Verified signaturecef25b3 -
Re-pack Falcon-H1-3B-Instruct_int8.litertlm: llm_model_type qwen2p5, tool-result rendering and a JSON tool-call example in the chat template (metadata only; tool calls parse and tool results reach the model on litert-lm 0.18.0)
Verified signatured8c58df -
litertlm_manifest.json: known_issues now carry the runtime notes added to the card on 2026-10-12/13 — one Engine per conversation (LiteRT-LM #3165)
Verified signature5979909
22 days ago
-
Card: one Engine per conversation on LiteRT-LM (own report #3165), measured on litert-lm 0.18.0
Verified signature6b3cc29
27 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 signature604fe33
-
Chat template: accept the 0.18 content-parts form (string form unchanged); weights, tokenizer and executor metadata byte-identical
Verified signature92693d1
-
Card: measured device / browser results (edge-compat, 2026-09)
Verified signature182c11f -
Card: compatibility line (edge-compat, 2026-09)
Verified signature793748a
-
Add litertlm_manifest.json (deployment manifest 0.1.2: variant selection, verified backends, Android/Apple recommendations, measured rows with conditions)
Verified signaturee4e8334 -
Card: base_model_relation: quantized (list under the base model's Quantizations)
Verified signaturee41838b
-
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.8e47d0c
-
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.fa7018f
-
Card: state where GPU execution is verified, and scope the Android decode note
Verified signatured64b51d
-
Falcon-H1-3B int8 (fp32act, full prefill ladder)
Verified signature4caff0e -
Falcon-H1-3B LiteRT-LM card
Verified signature36befba -
initial commit
Verified signaturea066577