{"adoption": {"forks": 414, "observed_at": "2026-08-28T04:09:33.779300+00:00", "stars": 5967}, "canonical_url": "https://ross.abutalabs.com/products/dflash", "card": {"archived": false, "artifact_type": "library", "description": "DFlash: Block Diffusion for Flash Speculative Decoding", "domain": ["large-language-models", "machine-learning", "deep-learning", "performance"], "enriched": true, "function": ["llm-inference", "machine-learning", "deep-learning"], "health_score": 99, "homepage": "https://dflash.z-lab.ai", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["z-lab/dflash"], "name": "z-lab/dflash", "platform": ["python"], "pushed_at": "2026-08-18T21:14:10+00:00", "repo": "z-lab/dflash", "stars": 5967, "tags": ["speculative-decoding", "block-diffusion", "llm-acceleration", "draft-model", "sglang", "vllm", "mlx", "transformers", "inference-optimization", "linux", "macos", "gpu", "docker"], "topics": [], "urls": [], "use_cases": ["speed up LLM inference with speculative decoding", "draft multiple tokens in parallel for a target LLM", "serve Qwen or Llama models with faster generation in SGLang", "benchmark speculative decoding speedups against EAGLE-3", "run lossless LLM acceleration on Apple Silicon with MLX", "use a diffusion-based draft model with vLLM or llama.cpp"], "what_it_is": "DFlash is a lightweight block diffusion model used as a draft model for speculative decoding of large language models, drafting entire token blocks in a single parallel forward pass. It ships as a pip-installable Python package with checkpoints for many model families and integrates with Transformers, MLX, SGLang, vLLM, oMLX, and llama.cpp serving backends.", "when_to_avoid": ["your target model family has no available DFlash checkpoint", "you need training or fine-tuning of the draft model rather than inference", "you cannot run a GPU or Apple Silicon backend"], "when_to_choose": ["you want lossless LLM inference speedups beyond autoregressive drafters like EAGLE-3", "your target model has an official DFlash checkpoint (Qwen, Gemma, Llama, Kimi, MiniMax, GLM, GPT-OSS)", "you serve models via SGLang, vLLM, oMLX, or llama.cpp OpenAI-compatible servers"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/dflash", "repo": "z-lab/dflash", "role": "main", "score": 71}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:33.779300+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:50:09.809566+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "546a0c4c4b2d9b29651d7b5d68b0a18a9079ef6af24de7e0b4110bb193d82125", "fetched_at": "2026-08-28T04:09:33.779300+00:00", "kind": "readme", "missing": false, "url": "https://github.com/z-lab/dflash"}, {"content_hash": "546f39c97c3c74ee6f2e02dea3572715379bcfc391a90e21b874b424292c2202", "fetched_at": "2026-08-29T08:46:05.717230+00:00", "kind": "homepage", "missing": false, "url": "https://dflash.z-lab.ai"}, {"content_hash": "fa904852f2c7802988523943896f21613adcec7809c61e4541c511382e0d2632", "fetched_at": "2026-08-29T08:46:05.719993+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dflash/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:33.779300+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:50:09.809566+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "546a0c4c4b2d9b29651d7b5d68b0a18a9079ef6af24de7e0b4110bb193d82125", "fetched_at": "2026-08-28T04:09:33.779300+00:00", "kind": "readme", "missing": false, "url": "https://github.com/z-lab/dflash"}, {"content_hash": "546f39c97c3c74ee6f2e02dea3572715379bcfc391a90e21b874b424292c2202", "fetched_at": "2026-08-29T08:46:05.717230+00:00", "kind": "homepage", "missing": false, "url": "https://dflash.z-lab.ai"}, {"content_hash": "fa904852f2c7802988523943896f21613adcec7809c61e4541c511382e0d2632", "fetched_at": "2026-08-29T08:46:05.719993+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dflash/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:50:09.809566+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "546a0c4c4b2d9b29651d7b5d68b0a18a9079ef6af24de7e0b4110bb193d82125", "fetched_at": "2026-08-28T04:09:33.779300+00:00", "kind": "readme", "missing": false, "url": "https://github.com/z-lab/dflash"}, {"content_hash": "546f39c97c3c74ee6f2e02dea3572715379bcfc391a90e21b874b424292c2202", "fetched_at": "2026-08-29T08:46:05.717230+00:00", "kind": "homepage", "missing": false, "url": "https://dflash.z-lab.ai"}, {"content_hash": "fa904852f2c7802988523943896f21613adcec7809c61e4541c511382e0d2632", "fetched_at": "2026-08-29T08:46:05.719993+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dflash/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:33.779300+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:33.779300+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:33.779300+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:50:09.809566+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "546a0c4c4b2d9b29651d7b5d68b0a18a9079ef6af24de7e0b4110bb193d82125", "fetched_at": "2026-08-28T04:09:33.779300+00:00", "kind": "readme", "missing": false, "url": "https://github.com/z-lab/dflash"}, {"content_hash": "546f39c97c3c74ee6f2e02dea3572715379bcfc391a90e21b874b424292c2202", "fetched_at": "2026-08-29T08:46:05.717230+00:00", "kind": "homepage", "missing": false, "url": "https://dflash.z-lab.ai"}, {"content_hash": "fa904852f2c7802988523943896f21613adcec7809c61e4541c511382e0d2632", "fetched_at": "2026-08-29T08:46:05.719993+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dflash/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:33.779300+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:33.779300+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:50:09.809566+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "546a0c4c4b2d9b29651d7b5d68b0a18a9079ef6af24de7e0b4110bb193d82125", "fetched_at": "2026-08-28T04:09:33.779300+00:00", "kind": "readme", "missing": false, "url": "https://github.com/z-lab/dflash"}, {"content_hash": "546f39c97c3c74ee6f2e02dea3572715379bcfc391a90e21b874b424292c2202", "fetched_at": "2026-08-29T08:46:05.717230+00:00", "kind": "homepage", "missing": false, "url": "https://dflash.z-lab.ai"}, {"content_hash": "fa904852f2c7802988523943896f21613adcec7809c61e4541c511382e0d2632", "fetched_at": "2026-08-29T08:46:05.719993+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dflash/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:33.779300+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:33.779300+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:33.779300+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:50:09.809566+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "546a0c4c4b2d9b29651d7b5d68b0a18a9079ef6af24de7e0b4110bb193d82125", "fetched_at": "2026-08-28T04:09:33.779300+00:00", "kind": "readme", "missing": false, "url": "https://github.com/z-lab/dflash"}, {"content_hash": "546f39c97c3c74ee6f2e02dea3572715379bcfc391a90e21b874b424292c2202", "fetched_at": "2026-08-29T08:46:05.717230+00:00", "kind": "homepage", "missing": false, "url": "https://dflash.z-lab.ai"}, {"content_hash": "fa904852f2c7802988523943896f21613adcec7809c61e4541c511382e0d2632", "fetched_at": "2026-08-29T08:46:05.719993+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dflash/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:33.779300+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:33.779300+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:50:09.809566+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "546a0c4c4b2d9b29651d7b5d68b0a18a9079ef6af24de7e0b4110bb193d82125", "fetched_at": "2026-08-28T04:09:33.779300+00:00", "kind": "readme", "missing": false, "url": "https://github.com/z-lab/dflash"}, {"content_hash": "546f39c97c3c74ee6f2e02dea3572715379bcfc391a90e21b874b424292c2202", "fetched_at": "2026-08-29T08:46:05.717230+00:00", "kind": "homepage", "missing": false, "url": "https://dflash.z-lab.ai"}, {"content_hash": "fa904852f2c7802988523943896f21613adcec7809c61e4541c511382e0d2632", "fetched_at": "2026-08-29T08:46:05.719993+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dflash/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:50:09.809566+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "546a0c4c4b2d9b29651d7b5d68b0a18a9079ef6af24de7e0b4110bb193d82125", "fetched_at": "2026-08-28T04:09:33.779300+00:00", "kind": "readme", "missing": false, "url": "https://github.com/z-lab/dflash"}, {"content_hash": "546f39c97c3c74ee6f2e02dea3572715379bcfc391a90e21b874b424292c2202", "fetched_at": "2026-08-29T08:46:05.717230+00:00", "kind": "homepage", "missing": false, "url": "https://dflash.z-lab.ai"}, {"content_hash": "fa904852f2c7802988523943896f21613adcec7809c61e4541c511382e0d2632", "fetched_at": "2026-08-29T08:46:05.719993+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dflash/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:50:09.809566+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "546a0c4c4b2d9b29651d7b5d68b0a18a9079ef6af24de7e0b4110bb193d82125", "fetched_at": "2026-08-28T04:09:33.779300+00:00", "kind": "readme", "missing": false, "url": "https://github.com/z-lab/dflash"}, {"content_hash": "546f39c97c3c74ee6f2e02dea3572715379bcfc391a90e21b874b424292c2202", "fetched_at": "2026-08-29T08:46:05.717230+00:00", "kind": "homepage", "missing": false, "url": "https://dflash.z-lab.ai"}, {"content_hash": "fa904852f2c7802988523943896f21613adcec7809c61e4541c511382e0d2632", "fetched_at": "2026-08-29T08:46:05.719993+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dflash/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:50:09.809566+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "546a0c4c4b2d9b29651d7b5d68b0a18a9079ef6af24de7e0b4110bb193d82125", "fetched_at": "2026-08-28T04:09:33.779300+00:00", "kind": "readme", "missing": false, "url": "https://github.com/z-lab/dflash"}, {"content_hash": "546f39c97c3c74ee6f2e02dea3572715379bcfc391a90e21b874b424292c2202", "fetched_at": "2026-08-29T08:46:05.717230+00:00", "kind": "homepage", "missing": false, "url": "https://dflash.z-lab.ai"}, {"content_hash": "fa904852f2c7802988523943896f21613adcec7809c61e4541c511382e0d2632", "fetched_at": "2026-08-29T08:46:05.719993+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/dflash/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 17, "rhythm": 66}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 241, "days_push": 15, "days_rel": 15, "gap_med": null, "n_releases_24m": 1}, "score": 71, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}