Search results

Evaluating Mixtral-8×7B-Instruct-v0.1-offloading-demo on MMLU

Status: Open.

#70 In EfficientMoE/MoE-Infinity;

· AugustXuan opened on Oct 23, 2025

what differences Between the GitHub Open-Source Version and the Paper Implementation of DeepSeek-Chat-Lite

Status: Open.

#68 In EfficientMoE/MoE-Infinity;

· dnnyyq opened on Oct 14, 2025

[BUG] CUDA Error: Invalid Device Ordinal on Single GPU Setup (NVIDIA RTX 3080)

bugSomething isn't workingSomething isn't working

Status: Open.

#67 In EfficientMoE/MoE-Infinity;

· ZiweiSong96 opened on Oct 8, 2025

Where is the func <code>prefetch_experts</code> called?

Status: Open.

#66 In EfficientMoE/MoE-Infinity;

· lshAlgorithm opened on Aug 2, 2025

[Feature Request] Improve cold start latency with ServerlessLLM sllm_store

enhancementNew feature or requestNew feature or request

Status: Open.

#65 In EfficientMoE/MoE-Infinity;

· drunkcoding opened on Jul 14, 2025

[Feature Request] Integrate FlashInfer for Prefill and Decode

enhancementNew feature or requestNew feature or request

Status: Open.

#64 In EfficientMoE/MoE-Infinity;

· lausannel opened on Jul 11, 2025

[BUG] Can't use pip to install moe-infinity.

bugSomething isn't workingSomething isn't working

Status: Open.

#61 In EfficientMoE/MoE-Infinity;

· YaoMu1995 opened on Jun 11, 2025

[Feature Request]How to measure the generation throughput(token/s)?

enhancementNew feature or requestNew feature or request

Status: Open.

#57 In EfficientMoE/MoE-Infinity;

· wuooo339 opened on Mar 25, 2025

[Feature Request]Explanation of Parallel Techniques

enhancementNew feature or requestNew feature or request

Status: Open.

#54 In EfficientMoE/MoE-Infinity;

· BaideBear opened on Mar 19, 2025

Does it support other DeepSeek models?

Status: Open.

#53 In EfficientMoE/MoE-Infinity;

· wuooo339 opened on Mar 18, 2025

[Feature Request] The Compatibility with DeepSeek V3

enhancementNew feature or requestNew feature or request

Status: Open.

#51 In EfficientMoE/MoE-Infinity;

· BaideBear opened on Mar 17, 2025

Question: Support for Continuous Batching and Asynchronous Requests

enhancementNew feature or requestNew feature or request

Status: Open.

#25 In EfficientMoE/MoE-Infinity;

· Msiavashi opened on Jun 12, 2024