sm89
Here are 11 public repositories matching this topic...
面向 8×RTX 4090(SM89)的 DeepSeek-V4-Flash-0731 MXFP4 SGLang 实验分支
-
Updated
Nov 16, 2026 - Python
4K video super-resolution on a 24 GB RTX 4090 — a free, local ComfyUI FlashVSR node (VIDEO in, VIDEO out) plus a Triton/FP8 operator pack at ~1.3×. No CUDA build, every number backed by benchmark JSONs.
-
Updated
Sep 28, 2026 - Python
Run DeepSeek-V4-Flash with 1M-token context on pre-Hopper NVIDIA GPUs (sm_89) — a vLLM 0.26.0 overlay replacing all SM90+ DeepGEMM/FlashMLA operators with Triton/TileLang/Marlin kernels + CPU-KV-pool (pinned host memory via CUDA UVA).
-
Updated
Oct 23, 2026 - Python
QSA HiSparse as an SGLang plugin: 256K CPU KV offload and text/image host prefix reuse for Qwen Sparse Attention on unmodified SGLang
-
Updated
Nov 3, 2026 - Python
RTX 4060 (Ada Lovelace / AD107 / sm_89) SM microarchitecture reverse-engineering: cycle-accurate microbenchmarks + SASS evidence
-
Updated
Nov 18, 2026 - Python
Feeding the Tensor Cores: a dense FP16 GEMM for NVIDIA Ada (sm_89) at 96.5% of cuBLAS, and what it teaches about how each GPU generation handles async copy and Tensor Core issue.
-
Updated
Aug 3, 2026 - Cuda
SMO.H3 Studio 的 SelfLift Spark 运行环境分发仓库(SM89 / SM120 运行包与环境清单)
-
Updated
Oct 31, 2026 - PowerShell
Port NInfer, a single-GPU CUDA inference engine, to the NVIDIA L20 (Ada sm_89, 92 SMs, 48 GB): patch set, build tooling, and measured results
-
Updated
Sep 20, 2026 - PowerShell
Add this topic to your repo
To associate your repository with the sm89 topic, visit your repo's landing page and select "manage topics."