Security Insights Additional navigation options 14Branches0Tags This branch is104 commits ahead of,3373 commits behindvllm-project/vllm:main. #4 Folders and files Name Last commit message Last commit date Latest commit chu-tianxiang tensor parallel for exl2 ...
A high-throughput and memory-efficient inference and serving engine for LLMs - Commits · chu-tianxiang/vllm-gptq
chu-tianxiang/QuIP-for-allPublic NotificationsYou must be signed in to change notification settings Fork5 Star40 QuIP This is an adaptation ofofficial quip-sharp repoto support a wider range of model architectures. There're a few changes making it incompatable with the checkpoints provided by qu...
Code Issues3 Pull requests1 Actions Projects Security Insights Additional navigation options Commit Browse filesBrowse the repository at this point in the history chu-tianxiangcommittedMar 2, 2024 1 parent3298625commit881a9d0 Show file tree Hide file tree ...
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm. - chu-tianxiang/AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm. - AutoGPTQ/examples/benchmark/generation_speed.py at db9eabfc4bf043e0713e996fb238d0d8bc4adbf5 · chu-tianxiang/AutoGPTQ
A high-throughput and memory-efficient inference and serving engine for LLMs - vllm-gptq/benchmarks/sonnet.txt at 45b6ef651387100c24d671fb485e7a6e208216f6 · chu-tianxiang/vllm-gptq
chu-tianxiang/vllm-gptq gptq_hf BranchesTags Code Folders and files Name Last commit message Last commit date Latest commit History 1,092 Commits .buildkite .github benchmarks cmake csrc docs examples rocm_patch tests vllm .dockerignore
chu-tianxiang/QuIP-for-allPublic NotificationsYou must be signed in to change notification settings Fork4 Star35 Folders and files Name Last commit message Last commit date Latest commit Cannot retrieve latest commit at this time. History
chu-tianxiang/AutoGPTQPublic forked fromAutoGPTQ/AutoGPTQ NotificationsYou must be signed in to change notification settings Fork0 Star1 MIT license starforks NotificationsYou must be signed in to change notification settings Code Pull requests ...