sm70

Here are 4 public repositories matching this topic...

vLLM for nVidia Volta (sm_70)

cuda pytorch cmp v100 bnb xformers vllm bitsandbytes autoround sm70 sm-70 100-210

Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.

benchmark cuda moe volta v100 fp8 vllm llm-inference tesla-v100 sm70

Serve Qwen3.5-397B-A17B (AWQ) on 8x Tesla V100-SXM2-32GB (DGX-1, TP8) for agentic coding & ops — a downstream fork of 1Cat-vLLM.

moe volta dgx-1 v100 awq vllm llm-inference qwen tesla-v100 sm70

VastLLM: a production-oriented FastLLM fork for native C++ inference, V100/SM70, long context, and Qwen3.5/3.6; upstream: ztxz16/fastllm

v100 llm-inference sm70 fastllm

Add a description, image, and links to the sm70 topic page so that developers can more easily learn about it.

To associate your repository with the sm70 topic, visit your repo's landing page and select "manage topics."