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 vllm-sm70 Public

   Forked from vllm-project/vllm

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

   Python

4. lmdeploy lmdeploy Public

   Forked from InternLM/lmdeploy

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

   Python

5. flash-attention-sm70 flash-attention-sm70 Public

   Forked from Dao-AILab/flash-attention

   Fast and memory-efficient exact attention

   Python

6. acme-relay acme-relay Public

   RFC 8555 ACME relay — give internal servers real Let's Encrypt certificates without per-host DNS credentials or public-CA reachability

   Go