DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to continue long chats without re-processing the context with Halogen Server

Use the prompt cache so follow-up turns on a long document resume instead of re-prefilling.

Short answer: Start the server with the default settings from the run command; then send the long document in the first chat request to /v1/chat/completions on port 8731; send a follow-up request in the same conversation that reuses the same earlier messages. All steps.

Who it is forA user or developer running long-document Q&A or a long multi-turn session on a local Strix Halo server.

The problemEach follow-up turn on a long context normally costs a full prefill, which dominates wait time at 32K tokens.

The outcomeFollow-up turns on a long conversation start quickly, with answers that match a cold run.

What you need first

  • AMD Strix Halo machine (Radeon 8060S class GPU, gfx1151) with /dev/kfd and /dev/dri available
  • Podman (or Docker with the video and render group flags described in the README)
  • About 36 GB of free disk for the 35.9 GB checkpoint, plus the 3.5 GB image
  • Python with pip to install the Hugging Face CLI

Steps

  1. Start the server with the default settings from the run command.
  2. Send the long document in the first chat request to /v1/chat/completions on port 8731.
  3. Send a follow-up request in the same conversation that reuses the same earlier messages.
  4. Compare time to first token for the first and follow-up requests.
  5. Set HALOGEN_CACHE_MB to 0 only if you want to disable the prompt cache for a comparison run.

Prompt for your agent

In the repo peonist-ai/halogen-server, run the halogen:0.1.4 server, send a long document from <document_path> as the first chat turn, then send the follow-up question <question> in the same conversation. Expected output: a faster time to first token on the follow-up than on the first turn. Verify that the follow-up answer is the same as a cold run with the cache disabled.

Caveat. The README gives roughly 20 times faster time to first token at 32K as a measured figure, so expect different gains on other prompt sizes.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for peonist-ai/halogen-server and "Continue long chats without re-processing the context"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer