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, and a one-script bootstrap.
☆37Aug 20, 2026Updated 2 months ago
Alternatives and similar repositories for glm-5.2-gb10
Users that are interested in glm-5.2-gb10 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- GLM-5.2-Int4-Int8 on 8x GB10 cluster☆39Jul 30, 2026Updated 2 months ago
- GLM-5.2 QuantTrio TP=4+DCP2 on 4x NVIDIA DGX Spark (GB10) — tuned and measured under a real agent workload. Adaptive MTP, the indexer law…☆19Aug 24, 2026Updated last month
- Wrap commands that might cause out-of-memory errors, and stop them before they freeze your machine☆15Sep 22, 2026Updated 3 weeks ago
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆90Oct 4, 2026Updated 2 weeks ago
- Ubuntu 24.04 + NVIDIA stack setup guide for GB10 / DGX Spark systems☆24Sep 22, 2026Updated 3 weeks ago
- 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.
- GLM-5.3-Flash NVFP4 on 4x NVIDIA DGX Spark: vLLM TP4, DFlash2 adaptive draft, measured FP8 vs NVFP4 vs EXL3 vs SGLang☆39Sep 29, 2026Updated 3 weeks ago
- Native DeepSeek V4.1 Flash inference across one RTX PRO 6000 and four DGX Spark expert workers☆36Sep 25, 2026Updated 3 weeks ago
- ☆41Aug 16, 2026Updated 2 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆42Updated this week
- DGX Spark (GB10/sm_121) port: DeepSeek-V4-Flash 159B on one Spark, GLM-5.2 753B across two. Prepacked 2-bit planes + unified-memory fixes…☆19Jul 20, 2026Updated 3 months ago
- Atlas Inference is a dependency free lightweight inference engine meant to run LLMs on YOUR compute seamlessly. Supports GB10 and Strix H…☆35Updated this week
- 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 2 months ago
- We gave AI models telepathy.☆18Sep 25, 2026Updated 3 weeks 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…☆33Updated this week
- 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.
- GLM-5.3-Flash EXL3 (320B MoE) on 2x NVIDIA DGX Spark — production serving kit, 1M context, 97%+ multi-session prefix caching, DFlash2 spe…☆62Oct 5, 2026Updated 2 weeks ago
- GLM-5.3 (full) on 3-6 DGX Sparks (GB10): a from-scratch CUDA inference engine☆38Updated this week
- DGX Spark (GB10) random hard power-off: how to diagnose the log-less crash signature and stop it with a GPU clock cap. Field-tested fix +…☆25Aug 16, 2026Updated 2 months ago
- A tiered-memory system design for workloads that don't fit in RAM: measure the working set, pin the hot tier, stream the cold tier from f…☆29Updated this week
- Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quan…☆140Updated this week
- vLLM inference solutions for NVIDIA GB10 (DGX Spark, sm121) — KIMI-K3 B12X_MLA + DSpark, GLM-5.2☆67Sep 30, 2026Updated 2 weeks ago
- Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 200K ctx with MTP spec decode on a 4x NVIDIA DGX Spark (GB10) cluster☆76Jul 25, 2026Updated 2 months ago
- GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.☆90Updated this week
- Userland fan control for NVIDIA DGX Spark, with additive RPM floors, a temperature-based curve, Secure Boot signing, and DKMS support.☆28Sep 8, 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.
- qwen38-flash-next recipe for tp=2 GB10☆127Oct 6, 2026Updated 2 weeks ago
- Optimized inference for the DGX Spark and spark clusters☆123Updated this week
- The prompt studio for AI filmmaking — plan shots, direct coverage, keep continuity, and compile production-ready prompts for any image, v…☆68Aug 9, 2026Updated 2 months ago
- 3D models for DGX cases☆54Aug 14, 2026Updated 2 months ago
- Fast, capable GLM-5.3-Flash FP4-Local on two DGX Sparks: opinionated Atlas serving and reproducible inference research.☆64Updated this week
- Headless / multi-user serving-mode for the DGX Spark: free unified memory for vLLM by paring back the desktop. Companion to qwen3.5-122B-…☆19Jun 29, 2026Updated 3 months ago
- Agent-ready two-node DGX Spark recipe for DeepSeek V4 Flash plus an optional Qwen Vision sidecar, with generic OpenAI-compatible, Hermes,…☆24Aug 10, 2026Updated 2 months ago
- AEON vLLM Ultimate — vLLM 0.27.1 built from source for DGX Spark / Blackwell (sm_121a/GB10). DSpark quantized Markov heads, DFlash SWA on…☆146Oct 6, 2026Updated 2 weeks ago
- Autonomous self-improving 4x DGX Spark (GB10) MoA stack + LoRA loop (DSV4F router, Qwen3.6/Omni/TwoTower/Gemma). Hermes MoA routing, ~90%…☆24Aug 17, 2026Updated 2 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Concurrency Patch to enable on DSpark - DeepSeek V4 Flash/Pro C=16 can be modified for more☆12Jun 29, 2026Updated 3 months ago
- agent multiplexer that lives in your terminal.☆14Updated this week
- Self-improving Codex loop: DeepSeek runs the task, Luna grades it, Sol rewrites the prompt until it is done☆47Sep 16, 2026Updated last month
- A reliability harness for running Pi coding agents with local language models.☆23Aug 30, 2026Updated last month
- Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, option…☆48Oct 13, 2026Updated last week
- CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark☆77Sep 4, 2026Updated last month
- Full GLM-5.3 (753B) served by TensorFold with tensor parallel 4 across four NVIDIA DGX Sparks: results, recipe, node settings, benches☆21Oct 13, 2026Updated last week