dflash2 repositories
Trending repositories tagged dflash2, ranked by trending score. Updated daily.
-
1
avifenesh/memra
Memra is a Rust + CUDA LLM inference engine with hand-written kernels, NVFP4 and mixed-precision execution, and correctness gates scoped to each model and GPU
GitHub · Rust · 7 stars · 1 forks · +1 stars in 24 hours · Trending score 0.63
-
2
inclusionAI/ASpec
A high-throughput training framework for Speculative decoding models.
GitHub · Python · 57 stars · 8 forks · 0 stars in 24 hours · Trending score 0.61
-
3
ARahim3/mlx-dspark
Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, ternary Bonsai-27B.
GitHub · Python · 736 stars · 63 forks · 0 stars in 24 hours · Trending score 0.02
-
4
Geramy/LSE
HRX, LOOM, Mac, and AMD running top speed kernels with a self optimizing engine.
GitHub · C++ · 29 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00
-
5
vukrosic/speculative-decoding-research
Evidence-first lab for speculative decoding, DFlash/DFlash2, block diffusion, exactness, acceptance, and inference performance
GitHub · Shell · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
6
jpezzulli/sglang-rtxpro6000
Optimized SGLang runtime for Qwen3.8-27B FP8 with DFlash2 and Qwen3.8 Flash-Next NVFP4 with FR-Spec on one NVIDIA RTX PRO 6000 Blackwell 96 GB GPU (SM120): 524K context, HiCache and NIXL.
GitHub · Python · 179 stars · 26 forks · 0 stars in 24 hours · Trending score 0.00
-
7
sxuff/qwen38-27b-nvfp4-dflash2-dgx-spark
Pinned stock Qwen3.8-27B NVFP4 + DFlash2 recipe and measured evidence for one NVIDIA DGX Spark
GitHub · Python · 21 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00
-
8
bemlerlabs/glm-5.3-flash-dgx-spark-dflash2
A practical recipe for serving GLM-5.3-Flash (320B MoE) on a single 128GB NVIDIA DGX Spark with DFlash2 speculative decoding.
GitHub · Shell · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
9
r0b0tlab/qwen38-exl3-dflash2
Qwen3.8-27B EXL3 (4.00 bpw) + DFlash2 speculative decoding for ExLlamaV3, validated at 262k context on a 24 GB RTX 3090
GitHub · Python · 25 stars · 3 forks · 0 stars in 24 hours · Trending score 0.00