What the posting requires
- Required
- Python
- C++
- Attention kernels
- KV cache
- Batching strategies
- Quantization
- vLLM
- CUDA
- Performance profiling tools
- Preferred
- Tensor parallelism
- Open-source
- Speculative decoding
- Mixture-of-experts routing
- Long-context serving
- Generative AI
These tags are our reading of the posting. They can miss something; the original posting is the reference.