Hand-written NVFP4 W4A16 CUDA kernels for Volta
NVIDIA Tesla V100 显卡驱动自动化管理套件
PXQ: PXA-native low-bit MoE quants (2/3/4-bit, E16-row scales) + fused CUDA kernels for Pascal/Volta — run a real 35B on a salvaged 12-16GB card. Fork of ik_llama.cpp.
Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.
Qwen3.8-27B in native NVFP4/FP8 on 2x PCIe Tesla V100-32GB (SM70): the PCIe runbook for v100-skinny + 1Cat-vLLM, with the 3 fixes that make it work without NVLink. 61-74 tok/s decode, MTP speculative decoding, OpenAI-compatible.
Multi-GPU acceleration for MiniMax H3 video generation on NVIDIA V100 (sm_70). Ulysses sequence parallelism as a drop-in ComfyUI custom node — ~19 min to ~7 min on 8x V100.
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.
SGLang fork for IBM POWER9 (ppc64le): Tesla V100 sm70, CUDA 12.4, Granite LLM inference. Triton attention, float16, OpenAI-compatible API.
Open hardware desktop AI node: 4× Tesla V100, 128GB HBM2, PCIe/NVLink topology and V-Core liquid/air cooling.
OpenAI Triton compiler fork for IBM POWER9/POWER10 (ppc64le) with CUDA 12.4. Tesla V100 sm70 GPU kernels for PyTorch and SGLang.
PyTorch 2.12 fork for IBM POWER9/POWER10 (ppc64le) with CUDA 12.4 and Triton. Tesla V100 sm70, GPU training and LLM inference.
Reproducible llama.cpp kernel and runtime optimization lab for dual NVIDIA Tesla V100 GPUs (SM70)
Run Mistral Voxtral realtime speech-to-text on a Tesla V100 (sm_70/Volta) via a patched vLLM — RTF ~0.4, keeps up real time
Running large LLMs on pre-Ampere NVIDIA hardware — Tesla V100 (sm_70), RTX 2080 Ti (sm_75), CMP 170HX. Measured benchmarks, vLLM forks, and the hardware side: NVLink on SXM2 carrier boards, driver traps, cooling, used-kit acceptance.
Add a description, image, and links to the tesla-v100 topic page so that developers can more easily learn about it.
To associate your repository with the tesla-v100 topic, visit your repo's landing page and select "manage topics."