void-main / fastertransformer_backend

Related projects: ⓘ

• void-main / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆58Updated last year
• OpenPPL / ppl.llm.serving
  ☆123Updated 3 months ago
• THUDM / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆39Updated last year
• Ascend / AscendSpeed
  ☆70Updated 9 months ago
• Rayrtfr / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆17Updated last year
• openppl-public / ppl.nn.llm
  ☆140Updated 4 months ago
• MoFHeka / LLaMA-Megatron
  A LLaMA1/LLaMA12 Megatron implement.
  ☆26Updated 9 months ago
• CoinCheung / gdGPT
  Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
  ☆90Updated 7 months ago
• alibaba / ChatLearn
  ☆105Updated last week
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆129Updated last week
• madsys-dev / deepseekv2-profile
  ☆60Updated last month
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆71Updated 6 months ago
• anyscale / llm-continuous-batching-benchmarks
  ☆108Updated 6 months ago
• genggui001 / Megatron-DeepSpeed-Llama
  ☆82Updated last year
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆78Updated 4 months ago
• ProjectD-AI / LLaMA-Megatron-DeepSpeed
  Ongoing research training transformer language models at scale, including: BERT & GPT-2
  ☆67Updated last year
• LLMServe / DistServe
  Disaggregated serving system for Large Language Models (LLMs).
  ☆278Updated last month
• Bruce-Lee-LY / flash_attention_inference
  Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
  ☆20Updated 2 weeks ago
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆41Updated last month
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆57Updated 2 months ago
• wejoncy / QLLM
  A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ, and export to onnx/onnx-runtime easily.
  ☆141Updated 3 weeks ago
• AlibabaPAI / FLASHNN
  ☆67Updated last week
• pcg-mlp / KsanaLLM
  ☆251Updated last week
• cli99 / llm-analysis
  Latency and Memory Analysis of Transformer Models for Training and Inference
  ☆338Updated 3 months ago
• zms1999 / SmartMoE
  A MoE impl for PyTorch, [ATC'23] SmartMoE
  ☆56Updated last year
• ModelTC / awesome-lm-system
  Summary of system papers/frameworks/codes/tools on training or serving large model
  ☆56Updated 9 months ago
• ninehills / llm-inference-benchmark
  LLM Inference benchmark
  ☆331Updated last month
• neuralmagic / AutoFP8
  ☆145Updated last month
• triton-inference-server / vllm_backend
  ☆170Updated this week
• feifeibear / long-context-attention
  USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
  ☆309Updated this week