-
Notifications
You must be signed in to change notification settings - Fork 33
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
- Status: Open.#146 In EfficientMoE/MoE-Infinity;
GLM-5.2 offload wrapper hard-depends on GlmMoeDsaMoE.route_tokens_to_experts (missing on some transformers 5.x)
bugSomething isn't workingSomething isn't workingStatus: Open.#144 In EfficientMoE/MoE-Infinity;Mixtral routed experts misclassified by
_is_routed_expert_keyregex (block_sparse_moe naming)bugSomething isn't workingSomething isn't workingStatus: Open.#142 In EfficientMoE/MoE-Infinity;- Status: Open.#123 In EfficientMoE/MoE-Infinity;
[BUG] moe-infinity on PyPI is a 0.0.1.dev0 placeholder — no real wheels published
bugSomething isn't workingSomething isn't workingStatus: Open.#114 In EfficientMoE/MoE-Infinity;[Feature Request] Improve cold start latency with ServerlessLLM sllm_store
enhancementNew feature or requestNew feature or requestStatus: Open.#65 In EfficientMoE/MoE-Infinity;Question: Support for Continuous Batching and Asynchronous Requests
enhancementNew feature or requestNew feature or requestStatus: Open.#25 In EfficientMoE/MoE-Infinity;