Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell
7 daysStars85124h gain+46Score29.5
Search
Find trending repositories by name or description.
8 results for “blackwell”
RankRepository7 daysStars24h gainScore
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
7 daysStars3.6k24h gain+1Score0.6
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.
7 daysStars19724h gain+1Score0.3
Collection of step-by-step playbooks for setting up AI/ML workloads on NVIDIA DGX Spark devices with Blackwell architecture.
7 daysStars95024h gain-Score0.0
MCP server that orchestrates language servers into agent-native workflows. 65 tools, 30 CI-verified languages.
7 daysStars16624h gain-Score0.0
Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support
7 daysStars18524h gain-Score0.0
A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official (NV)FP4 checkpoint's quality on consumer Blackwell cards
7 daysStars49824h gain-Score0.0
Offline NVIDIA Blackwell VBIOS editor.
7 daysStars19224h gain0Score0.0