focalcrest

Popular repositories Loading

1. vllm-marconi-offload vllm-marconi-offload Public

   Two-tier (RAM + SSD) KV cache offload for stock vLLM with Marconi-style reuse-aware eviction

   Python 2

2. Mixtile-EDGE2-Firmware Mixtile-EDGE2-Firmware Public

   EDGE2 Zigbee\Thread\Z-Wave gateway firmware

   1

3. vllm-sm70-docker vllm-sm70-docker Public

   Shell 1

4. mattermost-plugin-quote mattermost-plugin-quote Public

   Quote any Mattermost message from the hover toolbar, reply in your composer, click to jump back — with a correct in-place highlight instead of Mattermost's own scroll-jump bug.

   TypeScript 1

5. vllm-sm70 vllm-sm70 Public

   Forked from vllm-project/vllm

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python

6. lmdeploy lmdeploy Public

   Forked from InternLM/lmdeploy

   LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

   Python