antirez/ds4-style hybrid quant DeepSeek V4 Flash on a single DGX Spark via vLLM
☆17May 11, 2026Updated 5 months ago
Alternatives and similar repositories for ds4-spark-vllm
Users that are interested in ds4-spark-vllm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Optimized SGLang MoE kernel configs for NVIDIA DGX Spark (GB10) - GLM-4.7-FP8 and other MoE models☆13Feb 7, 2026Updated 8 months ago
- DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding☆53Oct 6, 2026Updated 3 weeks ago
- Qwen3.5-122B-A10B on a DGX Spark with DFlash speculative decode. One-shot Docker/vLLM installer. 80+ tok/s!☆59Jun 29, 2026Updated 4 months ago
- ☆28Aug 3, 2026Updated 2 months ago
- FlashQLA TileLang GDN kernels ported to NVIDIA Blackwell consumer (GB10 / DGX Spark)☆18Jun 5, 2026Updated 4 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- High-performance Qwen3.6-35B-A3B-DFlash inference on NVIDIA DGX Spark (~50 tok/s)☆13Apr 20, 2026Updated 6 months ago
- Headless / multi-user serving-mode for the DGX Spark: free unified memory for vLLM by paring back the desktop. Companion to qwen3.5-122B-…☆21Jun 29, 2026Updated 4 months ago
- Qwen3.6 27B × DFlash — 30-35 tok/s on NVIDIA DGX Spark (GB10) - LLama.Cpp☆17May 2, 2026Updated 5 months ago
- Fast cinematic video via LTX 2.3 22B. Single clips, full screenplays with character continuity, and sidechain-mixed final cuts.☆14Oct 6, 2026Updated 3 weeks ago
- Profile repo — categorized index of NVFP4 model releases, DGX Spark inference stacks, Apple Silicon MLX builds, the voice-AI stack, and t…☆41Oct 6, 2026Updated 3 weeks ago
- vLLM + Qwen3.5-122B-A10B-NVFP4 on NVIDIA DGX Spark (GB10/SM121) — single-GPU NVFP4 W4A4 with MTP speculative decoding, self-contained Doc…☆41Mar 12, 2026Updated 7 months ago
- Benchmarks, compose files, and findings for running Qwen3.6 (27B dense + 35B-A3B MoE) on 4× RTX 3090. vLLM/AWQ vs llama.cpp/GGUF, MTP spe…☆21Aug 15, 2026Updated 2 months ago
- Headless Matrix WebRTC voice AND video agent — auto-answers calls, bridges audio to any AI agent via PipeWire, optional camera-frame visi…☆20Oct 6, 2026Updated 3 weeks ago
- DSH 全双工语音插件：流式语音识别入草稿、语音合成按句朗读 + 实时字幕、开口即打断；本地识别免 API Key，可选唤醒词。 · Full-duplex voice plugin for DeepSeek Harness: streaming speech-to-tex…☆24Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- MiniMax-H3 on single DGX Spark: keys Sol-Engine ports + Heretic TE + Spectrum/Sage speed + 0.5MP upscaler finish. Formal bench included.☆49Aug 23, 2026Updated 2 months ago
- Archived: b12x development has moved to FlashInfer. See README for migration and PR-porting guidance.☆268Oct 6, 2026Updated 3 weeks ago
- Complete guide to running Qwen3.5-35B-A3B on NVIDIA DGX Spark (GB10) with vLLM - installation, benchmarks, vision features, and troublesh…☆100Mar 11, 2026Updated 7 months ago
- A userspace tunnel between two hosts mapping ports on client machine to addresses reachable from server machine.☆18Feb 25, 2022Updated 4 years ago
- "Defend your city by placing towers and destroying enemies!" 2D Tower Defense made with Godot☆26Sep 25, 2023Updated 3 years ago
- Alpine with ca-certificates installed☆11Nov 13, 2018Updated 7 years ago
- Ultra-low-latency, high-throughput multiprocess transport over SHM and mmap. LMAX-Disruptor-style cross-process ring substrate.☆22Aug 6, 2026Updated 2 months ago
- iOS app that syncs device's photos to an FTP NAS server☆10Nov 4, 2017Updated 8 years ago
- Object-storage-native KV cache for LLM inference & RL. Cross-restart, cross-conversation, cross-engine via shared S3 bucket.☆20Aug 10, 2026Updated 2 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- AEON vLLM Ultimate — vLLM 0.27.1 built from source for DGX Spark / Blackwell (sm_121a/GB10). DSpark quantized Markov heads, DFlash SWA on…☆148Oct 6, 2026Updated 3 weeks ago
- Run Qwen3.5-35B-A3B with llama.cpp and openclaw on NVIDIA DGX Spark (GB10)☆71Mar 1, 2026Updated 7 months ago
- WIP☆10Apr 11, 2021Updated 5 years ago
- Qwen3.8-27B NVFP4 on SGLang (DGX Spark / SM121): official image pin, native DSpark/EAGLE click-run, matched evals☆21Aug 19, 2026Updated 2 months ago
- Qwen 3.8 Flash NVFP4 with PLE NVFP4 quantized to run on a single DGX Spark☆15Aug 28, 2026Updated 2 months ago
- Optimized Qwen3.8-27B inference on NVIDIA DGX Spark☆16Sep 1, 2026Updated last month
- A parcel plugin for typed-css-modules - generate typescript declaration files for your css modules automatically☆15Sep 4, 2018Updated 8 years ago
- ☆21Sep 28, 2026Updated last month
- ☆17Aug 13, 2026Updated 2 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Dockerfile for stable-diffusion-webui with the goal of keeping it small and follow best practices. Works with A1111/Forge/Forge-Neo versi…☆38Jul 14, 2026Updated 3 months ago
- Run vLLM on 1-to-N NVIDIA DGX Spark servers (single Spark, 2 via direct cable, or 3+ via switched fabric) to serve or benchmark LLMs☆131Jun 22, 2026Updated 4 months ago
- Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpar…☆412Aug 27, 2026Updated 2 months ago
- Qwen3.8-27B NVFP4 (W4A16 shipped recipe) + MTP on NVIDIA DGX Spark GB10/SM121 — vLLM v0.27.2rc0, FP8 KV, 262K context, full reproducibili…☆27Aug 20, 2026Updated 2 months ago
- Kinda like other 2MQTT packages but for CUPS, the UNIX printing system☆14Oct 19, 2026Updated last week
- Optimized cross-platform expansion of autoresearch.☆18Mar 23, 2026Updated 7 months ago
- Sharing benchmarks from DGX stations☆29Sep 11, 2026Updated last month