iiis-turing-llm / llm-training-calculator
☆40Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for llm-training-calculator
- ☆199Updated this week
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆135Updated 5 months ago
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆90Updated 9 months ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆46Updated 3 months ago
- Multi-Candidate Speculative Decoding☆28Updated 6 months ago
- Repository of LV-Eval Benchmark☆46Updated 2 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆98Updated 4 months ago
- ☆63Updated 3 months ago
- ☆119Updated 9 months ago
- [ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.☆217Updated 2 weeks ago
- Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.☆96Updated this week
- FlagScale is a large model toolkit based on open-sourced projects.☆167Updated last week
- ☆36Updated last month
- ATC23 AE☆43Updated last year
- ☆82Updated last year
- The official code for paper "parallel speculative decoding with adaptive draft length."☆23Updated 2 months ago
- A LLaMA1/LLaMA12 Megatron implement.☆27Updated 11 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆350Updated 2 months ago
- Implement some method of LLM KV Cache Sparsity☆21Updated 5 months ago
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆278Updated last month
- MagicPIG: LSH Sampling for Efficient LLM Generation☆45Updated 2 weeks ago
- ☆313Updated 3 months ago
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆38Updated 8 months ago
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆309Updated last week
- [EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs☆216Updated 6 months ago
- Counting-Stars (★)☆76Updated 2 months ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆123Updated this week
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆76Updated last month
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆175Updated last month
- ☆70Updated 2 years ago