corpus.blog
56,966 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a0b0c5-082e-7027-9edf-b8a84720c2f3

Keeping vLLM's Prefix Cache Warm Between Agent Turns

doug.sh · published 15 September 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at doug.sh Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
16
Words captured
1,905

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
Tuning a Local Coding Agent: Oh My Pi and Qwen3.8-27B on Two RTX 3090s Read at the source ↗
doug.sh
https://github.com/can1357/oh-my-pi
github.com
https://github.com/maximhq/bifrost
github.com
https://github.com/maximhq/bifrost/pull/7170
github.com
https://github.com/mark3labs/mcp-go/pull/984
github.com
https://en.wikipedia.org/wiki/Chesterton%27s_fence
en.wikipedia.org
https://docs.vllm.ai/en/stable/features/automatic_prefix_caching/
docs.vllm.ai
https://docs.vllm.ai/en/stable/features/kv_offloading_usage/
docs.vllm.ai
https://github.com/vllm-project/vllm/issues/53670
github.com
https://github.com/vllm-project/vllm/issues/53504
github.com
https://github.com/vllm-project/vllm/blob/main/vllm/config/cache.py
github.com
https://github.com/maximhq/bifrost/issues/7169
github.com
https://github.com/mark3labs/mcp-go/issues/983
github.com
https://huggingface.co/Qwen/Qwen3.8-27B
huggingface.co
https://huggingface.co/dbirks/Qwen3.8-27B-W4A16-AutoRound
huggingface.co
https://github.com/syv-ai/qwen38-27b-rtx3090
github.com