Flint-DFlash2
incoai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
言語から画像、オープンウェイトからAPIまで。能力と実際の費用を比較。
次のアイデアに合うAIを見つけましょう。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
This repository contains the DFlash 2 draft model for `zai-org/GLM-5.3`. It is not a standalone language model: it runs inside a speculative decoding server and drafts tokens for the target model to verify. DFlash 2 is a block-diffusion drafter for speculative decoding. It predicts a whole block of tokens in a single pass and keeps the top candidates at every position. A lightweight selector then traces one coherent path through them. Two-tap dynamic convolutions in the backbone keep the draft from decaying toward the end of the block. Decoding is lossless: greedy output matches the target model exactly, and sampling preserves its distribution. DFlash 2 is also supported by vLLM v0.28.0 and later; see `incoai/GLM-5.3-NVFP4` for a vLLM serving example with the NVFP4-quantized target. See the blog post for more details.
翻訳待ち・原文を表示
This repository contains the DFlash 2 draft model for `zai-org/GLM-5.3-Flash`. It is not a standalone language model: it runs inside a speculative decoding server and drafts tokens for the target model to verify. DFlash 2 is a block-diffusion drafter for speculative decoding. It predicts a whole block of tokens in a single pass and keeps the top candidates at every position. A lightweight selector then traces one coherent path through them. Two-tap dynamic convolutions in the backbone keep the draft from decaying toward the end of the block. Decoding is lossless: greedy output matches the target model exactly, and sampling preserves its distribution. Benchmark numbers for this checkpoint are being re-measured and will be published here once final.
翻訳待ち・原文を表示
This repository contains an NVFP4-quantized version of Z.ai's `zai-org/GLM-5.3`. The weights and activations of the routed-expert linear layers are in NVFP4, and the KV cache is in FP8. The checkpoint uses the NVIDIA Model Optimizer format (`quant_method: modelopt`) and is served directly by SGLang and vLLM on NVIDIA Blackwell GPUs (SM100+). This checkpoint was produced with our in-house post-training quantization toolchain and exported in the NVIDIA Model Optimizer format. Only the weights and activations of the linear operators within the routed MoE experts are quantized to NVFP4, with static per-tensor activation scales. The KV cache is quantized to FP8 with static unit scales (`kv_cache_quant_algo: FP8`). The commands below enable speculative decoding with the DFlash 2 draft model (lossless, 7 draft tokens per verification step); remove the `--speculative-*` flags to serve without it.
翻訳待ち・原文を表示
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
This repository contains the DFlash 2 draft model for `Qwen/Qwen3.6-35B-A3B`. It is not a standalone language model: it runs inside a speculative decoding server and drafts tokens for the target model to verify. DFlash 2 is a block-diffusion drafter for speculative decoding. It predicts a whole block of tokens in a single pass and keeps the top candidates at every position. A lightweight selector then traces one coherent path through them. Two-tap dynamic convolutions in the backbone keep the draft from decaying toward the end of the block. Decoding is lossless: greedy output matches the target model exactly, and sampling preserves its distribution. We compare autoregressive decoding, Qwen3.6's built-in MTP with seven speculative steps, and DFlash 2. Both speculative methods propose seven draft tokens per verification step.
翻訳待ち・原文を表示
This repository contains the DFlash 2 draft model for `Qwen/Qwen3.8-27B`. It is not a standalone language model: it runs inside a speculative decoding server and drafts tokens for the target model to verify. The checkpoint is also mirrored at `z-lab/Qwen3.8-27B-DFlash2`. DFlash 2 is a block-diffusion drafter for speculative decoding. It predicts a whole block of tokens in a single pass and keeps the top candidates at every position. A lightweight selector then traces one coherent path through them. Two-tap dynamic convolutions in the backbone keep the draft from decaying toward the end of the block. Decoding is lossless: greedy output matches the target model exactly, and sampling preserves its distribution. See the blog post for other engines and more details.
翻訳待ち・原文を表示
This repository contains GGUF conversions of `incoai/Qwen3.8-27B-DFlash2`, the DFlash 2 draft model for `Qwen/Qwen3.8-27B`. It is not a standalone language model: it runs inside a speculative decoding server and drafts tokens for the target model to verify. The checkpoints are also mirrored at `z-lab/Qwen3.8-27B-DFlash2-GGUF`. DFlash 2 is a block-diffusion drafter for speculative decoding. It predicts a whole block of tokens in a single pass and keeps the top candidates at every position. A lightweight selector then traces one coherent path through them. Two-tap dynamic convolutions in the backbone keep the draft from decaying toward the end of the block. Decoding is lossless: greedy output matches the target model exactly, and sampling preserves its distribution. Build llama.cpp with DFlash 2 support (PR #27342):
翻訳待ち・原文を表示
This repository contains the DFlash 2 draft model for `Qwen/Qwen3.8-Flash-Next`. It is not a standalone language model: it runs inside a speculative decoding server and drafts tokens for the target model to verify. DFlash 2 is a block-diffusion drafter for speculative decoding. It predicts a whole block of tokens in a single pass and keeps the top candidates at every position. A lightweight selector then traces one coherent path through them. Two-tap dynamic convolutions in the backbone keep the draft from decaying toward the end of the block. Decoding is lossless: greedy output matches the target model exactly, and sampling preserves its distribution. Serve with SGLang. Flash-Next needs a small target-feature capture patch, included in this repository and validated at TP1, until support lands upstream:
翻訳待ち・原文を表示
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
提供元・分類・入出力の条件を変更してください。新しいモデルを随時追加しています。
月間トークン数を調整してAPI費用を比較。
収集済みの比較可能な100万トークン当たり米ドル料金です。キャッシュ割引、段階料金、追加推論出力、税金は含みません。最新料金は出典で確認してください。
入力・出力・キャッシュ料金を分け、同じ用途と使用量で総費用を比較します。画像・音声・動画は枚数、時間、解像度で課金される場合があります。
必ずしもそうではありません。バージョンごとのライセンス、商用制限、ポリシーを確認してください。自前運用には計算資源と保守費用も必要です。
順位はテスト、バージョン、評価方法によります。実際の業務データで精度、遅延、安定性、費用を比較してください。