No official torrent yet β requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from inclusionAI/Ling-3.0-flash-dspark
All models by inclusionAI βA DSpark speculator for Ling3. DSpark extends DFlash with target-model auxiliary features and a confidence head that dynamically chooses the number of draft tokens. The model was trained with SpecForge and is served with SGLang.
Acceptance length is the mean number of tokens accepted per speculative verification step, including the target bonus token.
The macro mean across the nine workload means is 5.29.
Launch recipes for this draft on every supported hardware/quantization cell β including the required --linear-replayssm-cache-len sizing β with measured speed and accuracy, are in the SGLang Ling-3.0-flash cookbook.
Use an SGLang version with DSPARK support. Replace the model paths and tensor-parallel size with values appropriate for your deployment:
Use a llama.cpp build with DSpark support. Replace the model paths, quantization type, and GPU layer counts with values appropriate for your deployment. First convert and quantize the target model:
Then generate the DSpark draft GGUF:
Finally, launch the server with the DSpark draft as the speculative model:
sglang serve \ --trust-remote-code \ --model-path <LING3_MODEL_PATH> \ --tp-size <TP_SIZE> \ --speculative-algorithm DSPARK \ --speculative-draft-model-path <LING3_DSPARK_MODEL_PATH> \ ......python convert_hf_to_gguf.py path/to/Ling-3.0-flash \ --outfile path/to/Ling-3.0-flash-bf16.gguf \ --outtype bf16 --model-name Ling-3.0-flash
llama-quantize \ path/to/Ling-3.0-flash-bf16.gguf \ path/to/Ling-3.0-flash-Q4_K_M.gguf \ Q4_K_Mpython convert_hf_to_gguf.py \ path/to/Ling-3.0-flash-dspark \ --target-model-dir path/to/Ling-3.0-flash \ --outtype bf16 \ --outfile path/to/Ling-3.0-flash-DSpark.ggufllama-server \ --model path/to/Ling-3.0-flash-Q4_K_M.gguf \ --spec-draft-model path/to/Ling-3.0-flash-DSpark.gguf \ --spec-type draft-dspark --spec-draft-n-max 8 \ -ngl all -ngld all -fa on