Hand-written NVFP4 W4A16 CUDA kernels for Volta
Agentic-coding oriented inference engine for N x V100-SXM2, based on SGLang: GLM-5.3-Flash, Qwen3.8-Flash-Next, DeepSeek-V4.1-Flash, MiniMax-H3.
Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.
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.
Reproducible llama.cpp kernel and runtime optimization lab for dual NVIDIA Tesla V100 GPUs (SM70)
Runbook + benchmarks: Qwen3.8-Flash-Next-ABLITERATED NVFP4 on 4× Tesla V100-32GB (reflashed SXM2→PCIe, 2+2 NVLink + PLX). 1Cat-vLLM 1.5.0, TP4 — 262,144-token context validated, 46 tok/s decode, 122 tok/s aggregate at 4 concurrent streams. Full E0–E17 optimization log with measured evidence.
双 V100 (SXM2/NVLink) 运行 Strata 引擎：Flash-Next 125B MoE SM70 实验通道编译移植、peer-tier 双卡部署实录与深度基准（解码 59~63 tok/s / Prefill 765 tok/s）
SGLang fork for IBM POWER9 (ppc64le): Tesla V100 sm70, CUDA 12.4, Granite LLM inference. Triton attention, float16, OpenAI-compatible API.
DP4A FlashAttention-2 and GEMM for Volta GPUs. 46 TOP/s INT8 on CMP 100-210 where tensor cores are firmware-disabled. The .superl8 format loads weights at memory speed.
V100 (sm_70) tuning kit for Ternary Bonsai 2 27B: q8_0-KV flash-attention direct read, D256 Split-D prefill kernel, PTQ1_0 planar mat-vec, MTP graft + draft micro-batch fix, ubatch presets. Prefill 175 -> 854 t/s, VRAM -1.9 GiB, PPL bit-identical (2-chunk). 中英双语 README (README.md / README.zh-CN.md).
Measured llama.cpp and quantization results on Tesla V100 (sm_70), Pascal GTX 1070, and RTX 4070 - hardware most projects don't test on
Run SeedVR2 video upscalers on Tesla V100 (Volta) — fixes the silent black-video fp16 bug with an FP16Safe-style patch.
[Unmaintained, use dg1kjd/sglang-sxm2] Qwen3.5-397B-A17B (AWQ) on 8x Tesla V100-SXM2-32GB with vLLM, a downstream fork of 1Cat-vLLM.
PyTorch 2.12 fork for IBM POWER9/POWER10 (ppc64le) with CUDA 12.4 and Triton. Tesla V100 sm70, GPU training and LLM inference.
To associate your repository with the sm70 topic, visit your repo's landing page and select "manage topics."