moe
17 Projekte teilen dieses GitHub-Topic
Linien verbinden Mitglieder, die messbar miteinander verwandt sind. Die Punktgröße spiegelt die Sterne wider.
🧬 Mitglieder
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
★ 95.7k
LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
★ 75.7k
sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
★ 38.2k
ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4,…
★ 16k
TensorRT-LLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and…
★ 15k
kimi-k3-in-c
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS,…
★ 9.2k
flashinfer
FlashInfer: Kernel Library for LLM Serving
★ 6.8k
GLM-4.5
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
★ 4.4k
MoBA
MoBA: Mixture of Block Attention for Long-Context LLMs
★ 2.2k
project-maya
Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B…
★ 2.1k · GitHub ↗
uccl
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL…
★ 1.5k
llm-architecture-from-scratch
Implementing LLM architectures from scratch in PyTorch
★ 1.1k · GitHub ↗
halo
Halo is an open-source framework built by White Circle for training large language and multimodal models
★ 833 · GitHub ↗
Chinese-Mixtral
中文Mixtral混合专家大模型（Chinese Mixtral MoE LLMs）
★ 613
step_into_llm
MindSpore online courses: Step into LLM
★ 480
halofpx
High-performance Lemonade alternative for AMD Strix Halo & Radeon — latest MoE models (Ling-3.0-Flash, Qwen…
★ 94 · GitHub ↗
llama.cpp-v100
llama.cpp optimized for NVIDIA Tesla V100 (SM70): Qwen3.8-Flash-Next with MTP (prefill 3402 tok/s at 200K…
★ 59 · GitHub ↗
🔗 Verwandte Familien
Gemessen anhand der von beiden Projekten geteilten GitHub-Themen, gewichtet nach der Seltenheit jedes Themas.