Zhanyl Abdybaeva
  • Blog
  • Lab Notes
  • Notes
  • Projects
  • Reading
  • About
  • Search

Tags

  • a100 1
  • agentic-ai 1
  • backfill 2
  • benchmark 1
  • cluster 1
  • cluster-operations 1
  • cuda 1
  • decoding 1
  • derivatives 1
  • distributed-training 1
  • fsdp 1
  • gitops 1
  • golang 3
  • gpu 8
  • gpu-inference 1
  • helm 1
  • hpc 7
  • inference 3
  • infiniband 1
  • kubernetes 2
  • kv-cache 2
  • langraph 1
  • llama 1
  • llm 1
  • llm-serving 1
  • lserve 1
  • mcp 1
  • memory 1
  • multi-node 1
  • nvidia 2
  • prefill 1
  • pricing 1
  • production 2
  • prometheus 3
  • python 1
  • pytorch 1
  • quantitative-finance 1
  • rdma 1
  • sampleattention 1
  • scheduling 2
  • slinky 1
  • slurm 7
  • sparse-attention 1
  • tensorrt-llm 1
  • upgrade 1
  • vllm 3
  • volatility 1
© 2026 Zhanyl Abdybaeva Github Linkedin X RSS