#

sm80

Here are 9 public repositories matching this topic...

promisezackr / glm53-flash-170hx-pp8

GLM-5.3-Flash (320B MoE) served with vLLM on 8x CMP 170HX (SM80, 64 GB, PCIe Gen2 x4): pipeline-parallel 8, NVFP4 weights, DFlash2 speculative decoding, 1M context. Patches, launch config and benchmarks.

moe pipeline-parallelism vllm llm-inference speculative-decoding nvfp4 glm-5 dflash cmp-170hx sm80 glm-5-3-flash

Updated Aug 31, 2026
Python

Ciender / CMP-170HX-SGLang-Qwen3.6-Benchmarks

Capacity-aware single-GPU SGLang benchmarks with MTP A/B, core/extended context matrices, raw telemetry, model/KV memory capture, and generated Markdown/PDF reports.

mtp qwen speculative-decoding sglang llm-benchmark cmp-170hx sm80

Updated Aug 1, 2026
Python

Mrzhiyao / glm53-a800-vllm

Reproducible vLLM deployment for GLM-5.3-Flash on 8x NVIDIA A800 SM80 GPUs

cuda glm vllm llm-inference a800 glm-5 sm80

Updated Aug 30, 2026
Python

Impactic48 / vllm-cmp170hx-tuning

Evidence-led vLLM tuning and qualification notes for NVIDIA CMP 170HX (sm80)

nvidia vllm llm-inference cmp-170hx sm80

Updated Aug 10, 2026

leinasi2014 / deepseek-v4-vision-cmp170hx

DeepSeek-V4-Flash-Vision-Exp on NVIDIA CMP 170HX/SM80 with vLLM, PP DSpark and 1M context

cuda vision-language-model vllm speculative-decoding deepseek-v4 cmp170hx sm80

Updated Sep 4, 2026
Python

t-sm0 / llama-cpp-a100-q6-kernels

Measured llama.cpp Q6_K CUDA optimizations for NVIDIA A100 (SM80)

cuda gpu-optimization llama-cpp nvidia-a100 sm80

Updated Sep 4, 2026

AG0708 / sgBLAS

Strict-FP32 CUDA SGEMM with shape-dispatched SM80 cp.async kernels and reproducible A100 evidence

performance-engineering cpp cuda matrix-multiplication high-performance-computing blas cuda-kernels gpu-computing sgemm a100 fp32 sm80

Updated Aug 21, 2026
Python

icyouo / Qwen3.8-Flash-Next-Dual-GPU

Native dual-GPU long-context inference runtime for Qwen3.8-Flash-Next

cuda dual-gpu long-context llm-inference qwen sm80

Updated Sep 2, 2026
Cuda

Leslie360 / GDN-QSA-sm80

From-scratch SM80 (A100/A800) CUDA kernels for GDN (Gated DeltaNet) and QSA (query-key sparse attention). Apache-2.0.

gdn ampere qsa a100 linear-attention cuda-kernel sparse-attention llm-inference sm80 gated-delta-rule

Updated Sep 7, 2026
Cuda

Add this topic to your repo

To associate your repository with the sm80 topic, visit your repo's landing page and select "manage topics."