Ashwin Sreedhar

What an agent can do with the emberserve corpus

ashwinsreedhar28/emberserve: From-scratch LLM inference engine: continuous batching, paged KV cache, prefix caching, hand-written Triton paged attention, CUDA graphs…

• Look up how emberserve implements continuous-batching, cuda-graphs, kv-cache, with answers cited to file and line.
• Reuse a worked example: the commit “cold start C, Qwen3-8B, fresh-trace sweeps” (26 files · JSON).
• Answer from emberserve's real JSON source instead of memory (AI, prompts and agents).

• Where does emberserve handle “cold start C, Qwen3-8B, fresh-trace sweeps”?
• How does emberserve implement continuous-batching?
• What does results do in emberserve?

Search the GitHub repository ashwinsreedhar28/emberserve with XERJ (https://hub.xerj.org/corpus/ashwinsreedhar28--emberserve).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/ashwinsreedhar28/emberserve emberserve && git -C emberserve checkout 440137e37e95ae294f88a6d50b72148fe1b267ce
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./emberserve --url http://127.0.0.1:9200 --prefix emberserve --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

corpus ashwinsreedhar28--emberserve · AI, prompts and agents
Related corpora: aider, p95labs/ifa, dynalm-project/dynalm
AI search and retrieval with XERJ · Case study: reference coding for agents