inference-optimization / dspark-inkling-small

huggingface.co
Total runs: 87
24-hour runs: 0
7-day runs: 7
30-day runs: 87
Model's Last Updated: September 04 2026

Introduction of dspark-inkling-small

Model Details of dspark-inkling-small

DSpark drafter for Inkling-Small-NVFP4

A DSpark speculative-decoding drafter trained for the verifier thinkingmachines/Inkling-Small-NVFP4 (multimodal MoE, NVFP4). DSpark drafts a whole block in one parallel pass (DFlash-style backbone) and injects intra-block dependency with a lightweight sequential Markov head, plus a per-position confidence head.

Model details
Algorithm DSpark (greedy proposal)
Verifier thinkingmachines/Inkling-Small-NVFP4
Backbone layers 6
Hidden size 4096
Attention heads / KV heads 32 / 8
Draft vocab size 201024 (full padded vocab)
Block size 16
Markov rank 256 (vanilla)
Confidence head enabled (with Markov)
Aux hidden-state layers 2, 10, 18, 26, 34, 39
dtype bfloat16
Acceptance evaluation

Inference acceptance measured with vLLM spec-decode over 9 task subsets (~300k drafts total). Mean acceptance length (AL) = expected number of tokens accepted per draft step (higher is better; block size 16).

Subset Acceptance length pos-0 pos-1 pos-2 pos-3 pos-4 pos-5 pos-6 pos-7
math_reasoning 4.55 0.776 0.611 0.476 0.376 0.297 0.232 0.182 0.141
HumanEval 3.90 0.740 0.533 0.389 0.288 0.215 0.165 0.129 0.101
rag 3.73 0.736 0.537 0.394 0.288 0.212 0.156 0.113 0.083
translation 3.56 0.736 0.535 0.382 0.269 0.188 0.132 0.094 0.067
summarization 3.40 0.731 0.530 0.375 0.265 0.178 0.119 0.077 0.050
tool_call 3.20 0.707 0.484 0.328 0.222 0.148 0.100 0.067 0.045
writing 3.11 0.679 0.447 0.296 0.198 0.136 0.095 0.068 0.050
qa 3.10 0.684 0.464 0.318 0.216 0.146 0.098 0.065 0.043
question 3.09 0.679 0.446 0.294 0.197 0.136 0.093 0.067 0.048
Average 3.40 0.709 0.493 0.344 0.241 0.170 0.121 0.087 0.063

Draft-weighted average across all subsets shown in the last row.

Per-position acceptance rate, draft-weighted mean over all subsets:

Per-position acceptance rate

Full per-position numbers are in acceptance_eval.csv .

Usage (vLLM)

Serve the verifier with this drafter as the speculative model:

vllm serve thinkingmachines/Inkling-Small-NVFP4 \
    --speculative-config '{"model": "<this-repo>", "num_speculative_tokens": 16}' \
    --enforce-eager \
    --trust-remote-code

Required vLLM patches (both open at time of writing):

  • vllm-project/vllm#52184 — adds Eagle3 hidden-state extraction support for Inkling (the verifier must expose the aux hidden states this drafter consumes).
  • vllm-project/vllm#55133 — treats a full/padded-vocab draft (draft vocab_size 201024 vs. the verifier's logical 200058) as an identity map, so no d2t mapping is required to load it.

Also note: Inkling currently requires --enforce-eager (CUDA-graph capture of the custom ops crashes).

Training

Trained with speculators for 3 epochs ( checkpoint_best = best validation epoch). Validation at the selected checkpoint: accept_len 3.67, accept_rate 0.40, pos-0 acc 0.776. Loss {"ce": 0.1, "tv": 0.9} , lr 1e-4, seq len 8192, block size 16.

Training curves (run dspark_inkling_small_v2 , logged with trackio):

Training curves

Provenance / reproducibility:

  • train_command.txt — exact training command, git SHA, and package versions (speculators 0.7.0.dev155, vllm 0.27.1, transformers 5.15.0, torch 2.13.0+cu130, compressed-tensors 0.17.0).
  • training_state.json — epoch / global step of this checkpoint.
  • val_metrics.json — full validation metrics.

Runs of inference-optimization dspark-inkling-small on huggingface.co

87
Total runs
0
24-hour runs
2
3-day runs
7
7-day runs
87
30-day runs

More Information About dspark-inkling-small huggingface.co Model

dspark-inkling-small huggingface.co

dspark-inkling-small huggingface.co is an AI model on huggingface.co that provides dspark-inkling-small's model effect (), which can be used instantly with this inference-optimization dspark-inkling-small model. huggingface.co supports a free trial of the dspark-inkling-small model, and also provides paid use of the dspark-inkling-small. Support call dspark-inkling-small model through api, including Node.js, Python, http.

inference-optimization dspark-inkling-small online free

dspark-inkling-small huggingface.co is an online trial and call api platform, which integrates dspark-inkling-small's modeling effects, including api services, and provides a free online trial of dspark-inkling-small, you can try dspark-inkling-small online for free by clicking the link below.

inference-optimization dspark-inkling-small online free url in huggingface.co:

https://huggingface.co/inference-optimization/dspark-inkling-small

dspark-inkling-small install

dspark-inkling-small is an open source model from GitHub that offers a free installation service, and any user can find dspark-inkling-small on GitHub to install. At the same time, huggingface.co provides the effect of dspark-inkling-small install, users can directly use dspark-inkling-small installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

dspark-inkling-small install url in huggingface.co:

https://huggingface.co/inference-optimization/dspark-inkling-small

Url of dspark-inkling-small

Provider of dspark-inkling-small huggingface.co

inference-optimization
ORGANIZATIONS

Other API from inference-optimization