LFM2.5-Encoder-350M-Prompt-Router — LiteRT

LiquidAI/LFM2.5-Encoder-350M-Prompt-Router converted to LiteRT (.tflite) for on-device inference. Zero-shot prompt routing: define your routing lanes as free text and the model scores the whole prompt against every lane in one CPU pass (demo Space).

Model description

File	Recipe	Size	Target
LFM2.5-Encoder-350M-Prompt-Router_wi8fc.tflite	int8 dynamic-range (linears + embedding, convs float)	365 MB	mobile + desktop
LFM2.5-Encoder-350M-Prompt-Router_fp16.tflite	fp16 weights, float compute	713 MB	desktop — phone memory limits (XNNPACK per-signature fp32 unpacking)

Two signatures, route_128 and route_512 (S = 128 / 512, batch 1, right-padded, up to 8 lane slots):

Tensor	Shape	Meaning
input_ids	int32 [1, S]	Categories:\n- <lane 1>\n- <lane 2>…\n\nText:\n<prompt>
attention_mask	int32 [1, S]	1 = real token, 0 = pad
text_pool	float32 [1, 1, S]	mean-pool weights over the prompt's own tokens (1/n each)
category_pool	float32 [1, 8, S]	row r = mean-pool weights over lane r's tokens; unused rows all-zero
output	float32 [1, 8]	one logit per lane slot

Softmax over the first N (real) lanes only — an all-zero pool row produces a constant bias logit that must be ignored.

How to use

1. Install dependencies

pip install ai-edge-litert numpy tokenizers huggingface_hub

2. Save the script below as route_prompt.py:

#!/usr/bin/env python3
"""Route a prompt to one of your lanes with litert-community/LFM2.5-Encoder-350M-Prompt-Router."""
import argparse

import numpy as np
from ai_edge_litert.interpreter import Interpreter
from huggingface_hub import hf_hub_download
from tokenizers import Tokenizer

REPO = "litert-community/LFM2.5-Encoder-350M-Prompt-Router"
MAX_LANES = 8


def build_inputs(text, lanes, tokenizer, seq_len):
    """Builds input_ids/attention_mask plus the two mean-pool matrices."""
    body = "\n".join(f"- {lane}" for lane in lanes)
    prefix = f"Categories:\n{body}\n\nText:\n"
    encoding = tokenizer.encode(prefix + text)
    ids, offsets = encoding.ids, encoding.offsets
    if len(ids) > seq_len:
        raise SystemExit(f"{len(ids)} tokens exceed --seq-len {seq_len}")

    input_ids = np.zeros((1, seq_len), np.int32)
    attention_mask = np.zeros((1, seq_len), np.int32)
    input_ids[0, : len(ids)] = ids
    attention_mask[0, : len(ids)] = 1

    # Mean-pool over the document's own tokens.
    text_pool = np.zeros((1, 1, seq_len), np.float32)
    text_idx = [i for i, (a, b) in enumerate(offsets) if b > len(prefix) and a != b]
    text_pool[0, 0, text_idx] = 1 / len(text_idx)

    # Mean-pool over each lane's tokens; unused lane rows stay all-zero.
    category_pool = np.zeros((1, MAX_LANES, seq_len), np.float32)
    pos = len("Categories:\n")
    for r, lane in enumerate(lanes):
        start, end = pos + 2, pos + 2 + len(lane)
        pos = end + 1
        idx = [i for i, (a, b) in enumerate(offsets) if a < end and b > start and a != b]
        category_pool[0, r, idx] = 1 / len(idx)

    return {
        "input_ids": input_ids,
        "attention_mask": attention_mask,
        "text_pool": text_pool,
        "category_pool": category_pool,
    }


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("--text", required=True, help="The prompt to route.")
    parser.add_argument("--lane", action="append", required=True,
                        help="A routing lane, repeatable (up to 8).")
    parser.add_argument("--seq-len", type=int, default=512, choices=[128, 512])
    args = parser.parse_args()
    if len(args.lane) > MAX_LANES:
        raise SystemExit(f"at most {MAX_LANES} lanes")

    model_path = hf_hub_download(REPO, "LFM2.5-Encoder-350M-Prompt-Router_wi8fc.tflite")
    tokenizer = Tokenizer.from_file(hf_hub_download(REPO, "tokenizer.json"))

    feed = build_inputs(args.text, args.lane, tokenizer, args.seq_len)
    interpreter = Interpreter(model_path=model_path)
    runner = interpreter.get_signature_runner(f"route_{args.seq_len}")
    logits = list(runner(**feed).values())[0][0]

    # Softmax over the real lanes only — unused rows carry a constant bias logit.
    real = logits[: len(args.lane)]
    probs = np.exp(real - real.max())
    probs /= probs.sum()
    for lane, p in sorted(zip(args.lane, probs), key=lambda x: -x[1]):
        print(f"{p:6.3f}  {lane}")


if __name__ == "__main__":
    main()

3. Run it

python route_prompt.py \
  --text "My Python script throws a KeyError on a dict lookup, how do I fix it?" \
  --lane "coding question" --lane "travel planning" \
  --lane "medical advice" --lane "small talk"

 0.838  coding question
 0.054  small talk
 0.054  travel planning
 0.054  medical advice

On Android/iOS use the LiteRT runtime's SignatureRunner APIs with the same signature names; the tokenizer is the standard Hugging Face tokenizer.json.

Performance

One pass over a padded sequence with the int8 (wi8fc) file, CPU only.

Device	Threads	route_128	route_512
Apple M4 Max (macOS)	8	34.5 ms	112.3 ms
iPhone 17 Pro	6	not measured	145 ms

Mac figures are the median of 20 warm runs (ai-edge-litert 2.1.6, XNNPACK, otherwise idle machine). The iPhone figure comes from the on-device gate (TFLite C API + SignatureRunner + XNNPACK) and is a single run, not a median.

Budget for one slow first call. The first inference after loading pays a one-time graph preparation: on the Mac it took 372 ms against a 34.5 ms steady state. Later signatures on the same loaded model do not pay it again — route_512 measured 110 ms cold against 112 ms warm. Model load itself was 0.38 s on the iPhone, with a peak footprint of 649 MiB.

One pass scores the prompt against all eight lane slots at once, so the cost does not grow with the number of lanes. The signatures are fixed-shape, so input language or content does not change the time.

Accuracy note

Task-level parity against the PyTorch reference on the demo prompt with four lanes: fp32, fp16 and int8 all reproduce the reference lane probabilities to four decimal places — 0.838 for "coding question". That is a single-prompt spot check, not a benchmark over a labelled corpus.

On the iPhone 17 Pro the int8 file reproduces the desktop outputs bit-exactly — cosine 1.000000, max absolute difference 0.0.

License

LFM Open License v1.0 (see LICENSE, unchanged from the base model). Note the license's commercial-use threshold (Section 5). This repository redistributes converted Derivative Works of LiquidAI/LFM2.5-Encoder-350M-Prompt-Router with modification notices per Section 4; all credit for the model to Liquid AI.