Inkling DSpark speculator
Overview
A DSpark speculator for the Inkling NVFP4 target, enabling faster inference through speculative decoding. DSpark extends the DFlash parallel-draft backbone with a Markov logit-bias head and a per-position confidence head. This checkpoint was trained with SpecForge using hidden states from a live SGLang target engine.
Preview: This is a preview checkpoint. Official training and evaluation are in progress.
Model Specifications
- Base model: Inkling NVFP4; the exact matching target checkpoint and tokenizer are required.
- Format: Safetensors (single-file BF16, 1.93B trainable parameters + embedding + lm_head).
- Draft: 5 layers (Qwen3-style GQA), hidden 6144, 64 heads / 16 KV heads, head_dim 64, FFN 12288, rope_theta 8000000,
block_size=7. - Vocabulary: 200,058 tokenizer entries and 201,024 padded weight rows;
mask_token_id=200064. - DSpark heads: Markov rank 256 (vanilla) and confidence head (with-Markov).
- Aux hidden-state layers:
[5, 17, 35, 47, 59]. - Trained context: sequence length 4096.
- Target weights: target embedding and unembedding weights are not included in this checkpoint.
Evaluation Results
Acceptance length (acc_len) at temperature 0:
| Dataset | acc_len |
|---|---|
| GSM8K | 4.7585 |
| MATH500 | 4.1830 |
| HumanEval | 4.0504 |
| MBPP | 4.0577 |
| AIME25 | 3.4986 |
| MT-Bench | 3.2215 |
| LiveCodeBench | 3.1384 |
| Alpaca | 3.0479 |
| Arena-Hard-v2 | 3.0280 |
| Mean | 3.6649 |
Serving with SGLang
Requires a SGLang build (docker pull lmsysorg/sglang:dev-cu13-inkling-dspark) with DSpark support:
SGLANG_ENABLE_UNIFIED_RADIX_TREE=1 \
python -m sglang.launch_server \
--trust-remote-code \
--model-path thinkingmachines/Inkling-NVFP4 \
--tp 8 \
--quantization modelopt_fp4 \
--attention-backend fa4 \
--page-size 128 \
--fp4-gemm-backend flashinfer_trtllm \
--moe-runner-backend flashinfer_trtllm_routed \
--enable-torch-symm-mem \
--mamba-radix-cache-strategy extra_buffer \
--mem-fraction-static 0.68 \
--swa-full-tokens-ratio 0.1 \
--mamba-full-memory-ratio 0.1 \
--max-running-requests 68 \
--reasoning-parser inkling \
--tool-call-parser inkling \
--skip-server-warmup \
--speculative-algorithm DSPARK \
--speculative-draft-model-path RadixArk/Inkling-DSpark-Preview \
--speculative-draft-model-quantization unquant \
--chunked-prefill-size 8192 \
--cuda-graph-max-bs-prefill 8192 \
--disable-flashinfer-autotune \
--host 0.0.0.0 \
--port 30000
Training Details
- Framework: SpecForge online distillation with hidden states captured from the frozen Inkling target.
- Data: 400K Inkling regenerations from
open-perfectblend. - Schedule: up to 10 epochs, AdamW, peak learning rate
6e-4, cosine decay, 4% warmup, and gradient clipping at 1.0. - Loss:
0.1 CE + 0.9 L1 distillation + 1.0 confidence BCE, with 512 sampled anchors per sequence andblock_size=7.