tensor-parallelism repositories

Trending repositories tagged tensor-parallelism, ranked by trending score. Updated daily.

  1. 1
    NVIDIA-NeMo/labs-molt

    A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).

    GitHub · Python · 1,398 stars · 154 forks · +38 stars in 24 hours · Trending score 3.11

  2. 2
    bertholomus/deepseek-v4.1-tensorfold-tp2-2xgb10

    BertholomusAI recipe: DeepSeek-V4.1-Flash-1017 on 2x NVIDIA DGX Spark (GB10), our own TensorFold TP2 engine. Weights: bertholomus EXL3 2.5bpw quant (MIT). v0.7.5.

    GitHub · Python · 73 stars · 7 forks · +33 stars in 24 hours · Trending score 2.64

  3. 3
    christopherowen/dgx-spark-networking

    Switchless RoCE collectives, NCCL profiles and fabric tooling for DGX Spark inference recipes

    GitHub · Python · 45 stars · 4 forks · 0 stars in 24 hours · Trending score 0.64

  4. 4
    Lowaltitudeflight/local-llm-tuning-guide

    A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative decoding, KV cache. Every conclusion carries its evidence grade and reproducible conditions.

    GitHub · Python · 80 stars · 0 forks · 0 stars in 24 hours · Trending score 0.47

  5. 5
    doctomoe2019/strix-dual-exp

    Two-rank tensor-parallel LLM serving over USB4v2 between AMD Strix Halo hosts: a custom Linux thunderbolt stream transport, self-healing link, and gufo TP2 integration

    GitHub · C · 17 stars · 0 forks · +1 stars in 24 hours · Trending score 0.46

  6. 6
    Bizuayeu/GLM-5.3-Flash-DGX-Sparks-BIZ

    GLM-5.3-Flash BIZ for DGX Spark-class GB10 systems. 3.x serves Jammed XSFP4 at TP=2 and XSFP4 at TP=3 and TP=4 with TensorFold's native Zig/CUDA engine (MTP drafts equal serial, tool calls, structured output, images, video). Apache-2.0 code, weights fetched separately. BIZ = business-use intent, not support or certification.

    GitHub · Python · 16 stars · 3 forks · 0 stars in 24 hours · Trending score 0.26

  7. 7
    gty111/gLLM

    An Efficient and Versatile Inference Engine for Distributed LLM Serving

    GitHub · Python · 74 stars · 9 forks · 0 stars in 24 hours · Trending score 0.18

  8. 8
    Havensky-stack/windows-ninfer-V100X2

    面向 Windows 11 双 Tesla V100 的本地 Qwen 推理项目:原生 C++/CUDA、中文便携启动器、TP2 通信优化、实验 MTP/DFlash、OpenAI/Anthropic 兼容 API 与 TCC/WDDM 切换。基于 NInfer 上游独立维护。

    GitHub · C++ · 13 stars · 4 forks · 0 stars in 24 hours · Trending score 0.14

  9. 9
    Cedriceuh/freetoken-rdna3

    Fast local LLM inference on AMD Radeon RX 7900 XTX / XT (RDNA3, ROCm): big Mixture-of-Experts models like Qwen3.8-Flash-Next on one or two consumer GPUs. Up to 4 parallel agents with 262k context each, or one 1M-token context, OpenAI/Anthropic API, NVFP4 and EXL3 checkpoints. A tuned build of FreeToken.

    GitHub · Python · 12 stars · 0 forks · 0 stars in 24 hours · Trending score 0.05

  10. 10
    1115714829/llama.cpp-v100

    llama.cpp optimized for NVIDIA Tesla V100 (SM70). Qwen3.8-Flash-Next (MoE) with MTP on 1/2/3/6x V100-16GB at 262K context (6 GPUs: prefill 3402 tok/s at 200K; 2 GPUs on one socket: 2152 tok/s). Qwen3.8-27B with DFlash2 on 1-6 GPUs, up to 512K context. Multimodal, thinking, concurrent serving, built-in web UI.

    GitHub · C++ · 69 stars · 14 forks · 0 stars in 24 hours · Trending score 0.00

  11. 11
    WyvernTKC/llama.cpp-4xV100

    Fork of llama.cpp Nvida Volta V100 (tensor parallelism 4 x v100 GPU)

    GitHub · C++ · 12 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00