vLLM recipe: Xiaomi MiMo-V2.5 + DFlash speculative decoding + fp8 KV cache on 2x DGX Spark (GB10/sm_121)
☆10Jul 13, 2026Updated 4 months ago
Alternatives and similar repositories for mimo-v25-dflash-dgx-spark
Users that are interested in mimo-v25-dflash-dgx-spark are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- MiniMax M2.7 NVFP4 dual-GB10 Blackwell benchmark: vLLM FlashInfer-CUTLASS, public data, HTML canvas report, and Docker runtime.☆13May 24, 2026Updated 5 months ago
- Universal AI computer-control KVM (REST API + MCP) that drives any machine as plain USB hardware — nothing installed on the target. Built…☆20Updated this week
- GLM-5.2 (744B/40B MoE) on a 4× DGX Spark / GB10 (sm_121) cluster: portable Triton sparse-MLA kernels, a data-free expert prune, MTP draft…☆37Aug 20, 2026Updated 2 months ago
- ☆11Jun 16, 2026Updated 5 months ago
- Compiler benchmarking☆13Oct 27, 2017Updated 9 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 655,360-token context + MTP spec decode (DCP4, fp8_ds_mla) on a 4x NVIDIA DGX Spark …☆32Jul 13, 2026Updated 4 months ago
- ☆10Mar 27, 2017Updated 9 years ago
- ☆21Sep 28, 2026Updated last month
- Browser based app to convert text to LLM tokens☆11Updated this week
- UbiTok.io Smart Contracts (and tests)☆10Nov 26, 2017Updated 8 years ago
- A Deepseek V4 Flash 0731 / Vision Exp VLLM stack☆27Sep 24, 2026Updated last month
- GLM-5.3-Flash exlr8 (EXL3-trellis experts) serving recipe for GB10: vLLM + mentat, TP=1/2/3/4, exlr8 MoE kernels☆15Updated this week
- GLM-5.3-Flash (FP8) + DFlash2 speculative decoding on 4x NVIDIA DGX Spark / ASUS GX10: vLLM TP4, 256K context, switchless ConnectX-7 ring…☆30Oct 1, 2026Updated last month
- ☆12Aug 31, 2026Updated 2 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- fuse file system for google drive written in pure go☆14Jun 21, 2014Updated 12 years ago
- Misc repo for draft Solidity contracts.☆12Sep 19, 2018Updated 8 years ago
- Dockerized inference server and benchmarks for quantized Gemma 4 family on the NVIDIA DGX Spark (GB10). Features ARM64 CUDA 13 builds usi…☆13Jun 20, 2026Updated 4 months ago
- Build, load, and verify NCCL for switchless DGX Spark RoCE cycles☆21Oct 25, 2026Updated 3 weeks ago
- Collection of Line-by-Line commented code for completed Audits☆14Jun 15, 2019Updated 7 years ago
- Open Imi is a open source claude desktop alternative for developers, engineers and tech teams to hack MCP's and agents to their own likin…☆10Nov 16, 2025Updated last year
- ☆12Jul 13, 2026Updated 4 months ago
- ☆10Nov 8, 2018Updated 8 years ago
- Recover usable memory on DGX Spark with a 64 KiB kernel: an opt-in NVIDIA UVM page-table packing patch, build tools, and measured validat…☆40Oct 16, 2026Updated last month
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- SGLang optimizations for NVIDIA Spark (GB10) — SM121 Grace Blackwell☆13Updated this week
- A compilation of common and highly relevant questions for ICOs' FAQ section.☆11May 3, 2018Updated 8 years ago
- Native DeepSeek V4.1 Flash inference across one RTX PRO 6000 and four DGX Spark expert workers☆41Sep 25, 2026Updated last month
- Testbench for llama.cpp llama-server☆15Aug 20, 2025Updated last year
- Open quantization tooling for TurboQuant-style low-bit LLM releases, stock GGUF deployment, and Apple Silicon runtime experiments.☆10May 5, 2026Updated 6 months ago
- Qwen 3.8 Flash NVFP4 with PLE NVFP4 quantized to run on a single DGX Spark☆15Aug 28, 2026Updated 2 months ago
- ☆17Aug 16, 2026Updated 3 months ago
- GLM-5.2-Int4-Int8 on 8x GB10 cluster☆39Jul 30, 2026Updated 3 months ago
- English guide + one-command patcher for the vLLM spin-wait bug that overheats NVIDIA DGX Spark / GB10. Credit: nacyot. CPU cores spin at …☆24Aug 17, 2026Updated 3 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- A high-throughput and memory-efficient inference and serving engine for LLMs☆47Oct 27, 2026Updated 3 weeks ago
- FlashQLA TileLang GDN kernels ported to NVIDIA Blackwell consumer (GB10 / DGX Spark)☆18Jun 5, 2026Updated 5 months ago
- Plasma, Plasma Cash & Plasma XT implementation in Go☆14Oct 25, 2018Updated 8 years ago
- Test to see if a DGX Spark (or similar GB10 device) is throttling due to possible Power Delivery issues☆33Sep 28, 2026Updated last month
- Custom inference recipes for NVIDIA DGX Spark — Qwen 122B DFlash hybrid☆95Nov 3, 2026Updated 2 weeks ago
- MiMo-V2.5 Omni TP=2 on 2x DGX Spark · 1M context · NVFP4 4-bit KV (~1.97M-token KV pool @ 1M, ~30 tok/s) · 69-eval: thinking-OFF 97.8 bea…☆39Jul 13, 2026Updated 4 months ago
- Atlas Inference is a dependency free lightweight inference engine meant to run LLMs on YOUR compute seamlessly. Supports GB10 and Strix H…☆45Updated this week
Are these results useful?