Zanele Dlamini
zanele-d02
ยท
AI & ML interests
Efficient LLM inference, KV cache optimization, quantization, speculative decoding, model pruning
Recent Activity
liked a model about 18 hours ago
position-specialist-speculative-decoding/llama3-8b-instruct-poss3 liked a model about 18 hours ago
position-specialist-speculative-decoding/llama2-13b-chat-poss2 upvoted a paper about 18 hours ago
Knowledge Pull Requests for Continual Document AuthoringOrganizations
None yet