cmp-170hx

Here are 8 public repositories matching this topic...

Morrowmake / glm53-flash-cmp170hx-recipe

GLM-5.3-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 437 tok/s single-user, 841 tok/s at 8 users, 262K context, TP4 or PP4, one-command container install

moe glm ampere vllm local-llm speculative-decoding glm-5 cmp-170hx

Updated Oct 1, 2026
Shell

promisezackr / glm53-flash-170hx-pp8

Star

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

redlinedtm-jpg / vllm-v100-2080ti-recipes

Star

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.

cuda benchmarks turing volta nvlink awq tensor-parallelism llm gpu-server llama-cpp vllm local-llm llm-inference tesla-v100 rtx-2080ti gpu-hardware cmp-170hx sxm2 ga100

Updated Aug 19, 2026

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

Star

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

kaka86mm / dsv4-vision-170hx

Star

DeepSeek-V4-Flash-Vision-Exp multimodal serving on 4× CMP 170HX (unlocked GA100, sm_80, PP4, 512k ctx, DSpark)

inference ampere multimodal a100 vllm deepseek cmp-170hx

Updated Sep 8, 2026
Python

Morrowmake / vllm-cmp170hx

Star

vLLM for NVIDIA CMP 170HX (Ampere sm_80): fast, repeatable model serving on one card or several

cuda nvidia glm ampere multi-gpu pipeline-parallelism tensor-parallelism sparse-attention vllm llm-inference speculative-decoding cmp-170hx sm80

Updated Oct 1, 2026
Python

Hurricane-Computer / cmp170hx-dda-gen2

Star

Boot-time PCIe Gen2 workaround for NVIDIA CMP 170HX 40GB/64GB in Linux guests under Windows Hyper-V DDA.

linux nvidia windows-server dda hyper-v pcie cmp-170hx

Updated Sep 7, 2026
C

magicsmokepress / cmp-170hx-vllm

Star

64 GB of HBM2e on a dead mining card: running Qwen3-Next-80B on an NVIDIA CMP 170HX with vLLM. Configs, gotchas, and measured benchmarks.

benchmark gpu nvidia homelab a100 llm-serving vllm local-llm llm-inference qwen cmp-170hx mining-gpu

Updated Sep 22, 2026
Python

Add this topic to your repo

To associate your repository with the cmp-170hx topic, visit your repo's landing page and select "manage topics."

Learn more