Cross-Family Speculative Decoding for Polish Language Models on Apple~Silicon: An Empirical Evaluation of Bielik~11B with UAG-Extended MLX-LM

• URL: http://arxiv.org/abs/2604.16368v2
• Date: Tue, 21 Apr 2026 17:25:47 GMT
• Title: Cross-Family Speculative Decoding for Polish Language Models on Apple~Silicon: An Empirical Evaluation of Bielik~11B with UAG-Extended MLX-LM
• Abstract summary: We extend the MLX-LM framework with Universal Assisted Generation (UAG) to enable cross-tokenizer speculative decoding on Apple Silicon.<n>Experiments on three Polish-language datasets (Wikipedia, pl_alpaca, synthetic) use draft lengths k in 2, 4, 6 to compare naive and context-aware token translation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Speculative decoding accelerates LLM inference by using a small draft model to propose k candidate tokens for a target model to verify. While effective for same-tokenizer pairs on high-bandwidth GPUs, its applicability to cross-family pairs with mismatched tokenizers and consumer-grade unified memory remains underexplored. We extend the MLX-LM framework with Universal Assisted Generation (UAG) to enable cross-tokenizer speculative decoding on Apple Silicon. We evaluate Bielik 11B-Instruct (Mistral-based) as the target model, paired with three draft models: Bielik 1.5B (Qwen-based with custom tokenizer), Qwen2.5-1.5B, and Llama 3.2-1B. Experiments on three Polish-language datasets (Wikipedia, pl_alpaca, synthetic) use draft lengths k in {2, 4, 6} to compare naive and context-aware token translation. Results show: (1) context-aware translation consistently improves acceptance rates across all configurations; (2) the Polish-specialized Bielik 1.5B achieves lower acceptance than general-purpose Qwen2.5 and Llama 3.2 drafters; (3) throughput on Apple Silicon is content-dependent, reaching 1.7x speedup for structured text but failing for varied instructions; and (4) verification cost on unified memory does not amortize as theory predicts because both models are memory-bandwidth bound, making sequential drafting expensive relative to batched verification. We propose a hardware-aware speedup formula and characterize conditions for cross-family speculative decoding on Apple Silicon. This is the first systematic evaluation of cross-family speculative decoding for Polish LLMs and the first empirical study of UAG-based decoding on unified memory architectures.

Related papers

• Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Sampling [11.823547220829083]
  Diffusion large language models (dLLMs) offer a promising parallel decoding paradigm as an alternative to autoregressive generation.<n>We propose an "early-bird (EB)" decoding framework, motivated by the observation that tokens with similarly low entropy tend to cluster.<n>EB-Decode integrates two key enablers: (1) a learnable network that adaptively groups tokens with similar uncertainty into variable-length blocks, rather than relying on fixed block sizes; and (2) a position-aware sampler that learns to unmask tokens in parallel using fewer decoding steps within predicted variable-length blocks.
  arXiv  Detail & Related papers  (2026-09-15T00:12:37Z)
• Architecture-Dependent Causal Transfer of Activation States Across Large Language Models [51.56484100374058]
  Internal language activation states can be transferred causally between different large language models.<n>Injecting projected activations into a target model during generation produces a statistically significant, preregistered causal effect.<n>We conclude that end-to-end activation-state transfer between LLMs, as currently implemented, is architecture-dependent rather than universal.
  arXiv  Detail & Related papers  (2026-08-17T09:53:27Z)
• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• SimSD: Simple Speculative Decoding in Diffusion Language Models [61.33773959352141]
  Diffusion large language models (dLLMs) offer faster inference through parallel or blockwise decoding.<n>Their masked language modeling formulation remains incompatible with standard token-level speculative decoding.<n>We propose a speculative decoding algorithm for dLLMs, named SimSD, that equips dLLMs with temporally valid token-level contexts.<n>Our method achieves up to 7.46x higher decoding throughput while maintaining and even improving average generation quality.
  arXiv  Detail & Related papers  (2026-06-01T17:46:46Z)
• Predict and Reconstruct: Joint Objectives for Self-Supervised Language Representation Learning [0.0]
  Masked language modelling (MLM) has been the dominant pre-training objective for text encoders since BERT.<n>Inspired by the success of Joint Embedding Predictive Architectures (JEPA) in vision and audio, we propose a hybrid objective.<n>We pre-train both a hybrid model and a pure-MLM baseline on English Wikipedia using identical architectures and compute budgets.
  arXiv  Detail & Related papers  (2026-04-16T22:26:47Z)
• BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, Rerankers and LLMs [0.0]
  Zero-shot text classification (ZSC) offers the promise of eliminating costly task-specific annotation.<n>Recent advances in text-embedding models, rerankers, and instruction-tuned large language models (LLMs) have challenged the dominance of NLI-based architectures.<n>We introduce BTZSC, a comprehensive benchmark of 22 public datasets spanning sentiment, topic, intent, and emotion classification.
  arXiv  Detail & Related papers  (2026-03-12T14:43:20Z)
• BRIDGE: Building Representations In Domain Guided Program Verification [67.36686119518441]
  BRIDGE decomposes verification into three interconnected domains: Code, Specifications, and Proofs.<n>We show that this approach substantially improves both accuracy and efficiency beyond standard error feedback methods.
  arXiv  Detail & Related papers  (2025-11-26T06:39:19Z)
• Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models [51.12873073612084]
  Masked Diffusion Models (MDMs) as language models generate by iteratively unmasking tokens, yet their performance depends on the inference time order of unmasking.<n>We propose Lookahead Unmasking (LookUM), which addresses these concerns by reformulating sampling as path selection over all possible unmasking orders.<n>LookUM requires only two to three paths to achieve peak performance, demonstrating remarkably efficient path selection.
  arXiv  Detail & Related papers  (2025-11-04T02:37:37Z)
• S*: Test Time Scaling for Code Generation [55.11863577956177]
  We propose S*, the first hybrid test-time scaling framework for code generation.<n>S* substantially improves the coverage and selection accuracy of generated code.
  arXiv  Detail & Related papers  (2025-02-20T09:18:53Z)
• Falcon: Faster and Parallel Inference of Large Language Models through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree [7.438117410146904]
  Falcon is an innovative speculative decoding framework fashioned to augment both the drafter's parallelism and output quality.<n>Falcon incorporates the Coupled Sequential Glancing Distillation technique, which fortifies inter-token dependencies within the same block, leading to increased speculation accuracy.
  arXiv  Detail & Related papers  (2024-12-17T08:02:08Z)
• Advancing LLM Reasoning Generalists with Preference Trees [119.57169648859707]
  We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks.
  arXiv  Detail & Related papers  (2024-04-02T16:25:30Z)
• SDSAT: Accelerating LLM Inference through Speculative Decoding with Semantic Adaptive Tokens [4.5888031410244885]
  We propose an acceleration scheme for large language models (LLMs) through Speculative Decoding with Semantic Adaptive Tokens (SDSAT) The primary objective of this design is to enhance the LLM model's ability to generate draft tokens more accurately without compromising its accuracy. Experiments conducted on the CodeLlama-13B and 7B models have yielded speed increases of over 3.5X and 3.0X, respectively.
  arXiv  Detail & Related papers  (2024-03-27T14:54:27Z)
• Squeezeformer: An Efficient Transformer for Automatic Speech Recognition [99.349598600887]
  Conformer is the de facto backbone model for various downstream speech tasks based on its hybrid attention-convolution architecture. We propose the Squeezeformer model, which consistently outperforms the state-of-the-art ASR models under the same training schemes.
  arXiv  Detail & Related papers  (2022-06-02T06:06:29Z)
• FastLR: Non-Autoregressive Lipreading Model with Integrate-and-Fire [74.04394069262108]
  We propose FastLR, a non-autoregressive (NAR) lipreading model which generates all target tokens simultaneously. FastLR achieves the speedup up to 10.97$times$ compared with state-of-the-art lipreading model.
  arXiv  Detail & Related papers  (2020-08-06T08:28:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.