kvcache-ai / TrEnv-XLinks
☆73Updated 4 months ago
Alternatives and similar repositories for TrEnv-X
Users that are interested in TrEnv-X are comparing it to the libraries listed below
Sorting:
- Stateful LLM Serving☆95Updated 10 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆67Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆207Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆134Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆64Updated last year
- ☆83Updated 3 months ago
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆119Updated 3 weeks ago
- Accepted to MLSys 2026☆70Updated this week
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆87Updated last month
- A framework for generating realistic LLM serving workloads☆98Updated 3 months ago
- ☆75Updated last year
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆54Updated 5 months ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆90Updated 2 weeks ago
- A resilient distributed training framework☆96Updated last year
- Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport☆73Updated 8 months ago
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆79Updated 7 months ago
- ☆76Updated last week
- Microsoft Collective Communication Library☆66Updated last year
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆123Updated last month
- ☆50Updated 9 months ago
- ☆131Updated last year
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆25Updated last year
- Building the Virtuous Cycle for AI-driven LLM Systems☆140Updated this week
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny BERT model can tell you the verbosity of an …☆47Updated last year
- High-performance distributed data shuffling (all-to-all) library for MoE training and inference☆109Updated 3 weeks ago
- A simple calculation for LLM MFU.☆66Updated 4 months ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆41Updated 8 months ago
- SOTA Learning-augmented Systems☆37Updated 3 years ago
- ☆47Updated last year
- ☆164Updated 6 months ago