Prasad Khake
•
Writing
Work
Contact
← Writing
Topics
話題
browse 35 topics across the writing
on-device-llm
18
apple-silicon
17
mlx
17
benchmarks
6
kv-cache
4
quantization
4
benchmark
3
inference
3
speculative-decoding
3
diffusion
2
gemma
2
gemma4
2
llama
2
qwen3
2
apple
1
bandwidth
1
context-length
1
debugging
1
evaluation
1
fine-tuning
1
foundation-models
1
gpu-kernels
1
l4
1
llm-eval
1
lora
1
metal
1
mistral
1
mixture-of-experts
1
reasoning-models
1
streamingllm
1
tokenizers
1
tool-calling
1
turboquant
1
vllm
1
wwdc
1