Archived: b12x development has moved to FlashInfer. See README for migration and PR-porting guidance.
☆268Oct 6, 2026Updated 3 weeks ago
Alternatives and similar repositories for b12x
Users that are interested in b12x are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A high-throughput and memory-efficient inference and serving engine for LLMs☆44Updated this week
- Docker images for LLM inference (SGLang + vLLM) on NVIDIA Blackwell GPUs (SM120, CUDA 13.2)☆95Oct 20, 2026Updated last week
- RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink☆1,162Updated this week
- LLM inference decode throughput benchmark with Rich TUI dashboard. Measures token generation speed across concurrency levels and context …☆121Updated this week
- ☆17Jun 17, 2026Updated 4 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- 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
- ☆699Updated this week
- DeepSeek-V4-Flash-0731 tuned on 4x DGX Spark (GB10) at TP=4 — 123.13 tok/s decode. Every variable measured one at a time, with the values…☆13Aug 11, 2026Updated 2 months ago
- ☆17Aug 13, 2026Updated 2 months ago
- Native DeepSeek V4.1 Flash inference across one RTX PRO 6000 and four DGX Spark expert workers☆38Sep 25, 2026Updated last month
- FlashQLA TileLang GDN kernels ported to NVIDIA Blackwell consumer (GB10 / DGX Spark)☆18Jun 5, 2026Updated 4 months ago
- Agent-friendly GPU profile-query CLI☆130Oct 4, 2026Updated 3 weeks ago
- SGLang for GLM-5.3-Flash on two or four RTX PRO 6000 Blackwell GPUs (SM120), with TP2 W4A16 and TP4 NVIDIA NVFP4 profiles.☆47Oct 11, 2026Updated 2 weeks ago
- GLM-5.3-Flash NVFP4 on two or four DGX Sparks cabled as a ring, with no switch: the RiNGSiDE serving recipe☆30Sep 27, 2026Updated last month
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- GLM-5.2-Int4-Int8 on 8x GB10 cluster☆39Jul 30, 2026Updated 3 months ago
- 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
- antirez/ds4-style hybrid quant DeepSeek V4 Flash on a single DGX Spark via vLLM☆17May 11, 2026Updated 5 months ago
- Low-latency collective transport and distributed LLM serving stack for switchless GB10 clusters.☆101Oct 19, 2026Updated last week
- GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.☆94Updated this week
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆95Oct 22, 2026Updated last week
- Working recipe: MiniMax-M3 NVFP4 at tensor-parallel 3 across 3x DGX Spark (GB10/sm_121) with clean tool-calling. Includes the head-node O…☆16Jul 13, 2026Updated 3 months ago
- Docker configuration for running VLLM on dual DGX Sparks☆2,461Updated 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
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- MiniMax-M3 (428B, no pruning) at 36 tok/s on 2× NVIDIA DGX Spark — W4A16 GPTQ + NVFP4 KV + EAGLE-3 speculative decoding on vLLM. Three se…☆45Jul 13, 2026Updated 3 months ago
- Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, a…☆407Updated this week
- Pure Rust Inference Engine☆713Updated this week
- An ultra-fast, distributed Safetensors loader☆88Oct 13, 2026Updated 2 weeks ago
- Wrap commands that might cause out-of-memory errors, and stop them before they freeze your machine☆15Sep 22, 2026Updated last month
- Grafana dashboard for NVIDIA DGX Spark clusters running vLLM: throughput, contention, and GB10 GPU hardware telemetry (NVIDIA-themed, 55 …☆44Aug 18, 2026Updated 2 months ago
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆340Updated this week
- GLM-5.2 Quantrio INT4/INT8 Mixed Abliterated — SPEED=1 C1≈30 tok/s @ 128k on 4x DGX Spark. Step-by-step recipe, image bake, results.☆13Jul 18, 2026Updated 3 months ago
- Mixed-precision quantization for LLMs. Every layer refracts into a different format based on its sensitivity. Native compressed-tensors e…☆105Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Educational reference: NVIDIA Blackwell SM100 vs SM120, NVFP4, tcgen05, MoE inference on consumer Blackwell☆29Sep 3, 2026Updated last month
- GLM-5.3-Flash (NVFP4) at TP4 across 4x DGX Spark via a switchless RoCE ring + DFlash2 — reproducible recipe☆109Updated this week
- ☆37Apr 26, 2026Updated 6 months ago
- Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache☆167Sep 3, 2026Updated last month
- 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 3 months ago
- NVFP4 KV cache for vLLM on SM120 (RTX PRO 6000) via FlashInfer FA2 explicit-SF-stride patch — ~1.5x fp8 pool at ~95-104% speed☆20Jun 5, 2026Updated 4 months ago
- Two-node DGX Spark/ASUS GX10 DeepSeek V4 Flash DSpark NVFP4 port for vLLM 0.25, with live dashboard and reproducible deployment.☆82Updated this week