emgena/speculative_decoding_ngram_tree_drift_healer_teaser
Viewer • Updated • 50 • 54 • 5
Zanele Dlamini
zanele-d02
·
AI & ML interests
batching strategies, KV cache optimization
Recent Activity
upvoted a paper 1 day ago
Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand upvoted a paper 4 days ago
Factorized MLLM Embeddings for Composed Image RetrievalOrganizations
None yet
liked a
dataset 4 days ago
liked a
model 6 days ago
liked 2
Spaces 12 days ago
liked 3
Spaces 20 days ago
Reproduction: DFlash: Block Diffusion for Flash Speculative Decoding
🎯
5
Explore and collaborate on a research logbook online
Reproduction: FuseFSS: Efficient Secure LLM Inference with Function Secret Sharing
🎯
3
Explore, track, and share experiment logs in a web UI
Speculative Decoding Demo
🚀
9
Generate text with speculative decoding
liked a
dataset 21 days ago
liked a
dataset 24 days ago
liked a
model 29 days ago
liked 8
models about 1 month ago
SpeculativeDecoding/doctorboom-qwen2.5-coder-7b-lora
Updated • 15
shahzaibali-24/resume-quantization-model
67M • Updated • 13
inference4j/efficientnet-lite4
Image Classification • Updated • 13
position-specialist-speculative-decoding/llama2-13b-chat-poss3
Updated • 216 • 9
position-specialist-speculative-decoding/llama3-8b-instruct-poss1
Updated • 39 • 12
position-specialist-speculative-decoding/llama3-8b-instruct-poss3
Updated • 95 • 14
position-specialist-speculative-decoding/llama2-13b-chat-poss2
Updated • 330 • 15
praful-goel/speculative_decoding_models
Updated • 13
liked 2
models about 2 months ago