GLM-5.3-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 482.6 tok/s single-user, up to 943.7 tok/s at 8 users, 262K context, TP4 or PP4, one-command container install
☆89Oct 26, 2026Updated last week
Alternatives and similar repositories for glm53-flash-cmp170hx-recipe
Users that are interested in glm53-flash-cmp170hx-recipe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- glm-5.2 on too many 64 / 80 GB A100's☆22Sep 9, 2026Updated last month
- DeepSeek-V4-Flash-0731 on 4x CMP 170HX (sm_80): 98 tok/s decode, ~5300 tok/s prefill. DSpark speculative decoding under pipeline parallel…☆118Aug 13, 2026Updated 2 months ago
- Tuning and qualification harness for the NVIDIA CMP 170HX (GA100). Measures, gates and recovers clock/voltage settings, and treats a comp…☆96Sep 28, 2026Updated last month
- A tool to unlobotomize your NVIDIA card!☆31Sep 6, 2026Updated 2 months ago
- DeepSeek-V4.1-Flash (764B) on 4×CMP 170HX: PP4 + shadow KV + EXL3 2bpw + DSpark + 512k ctx + native vision — patches, recipes, acceptance…☆15Sep 29, 2026Updated last month
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Community-tested recipes, diagnostics, and benchmarks for CMP 170HX AI workloads☆97Oct 19, 2026Updated 2 weeks ago
- CMP 170HX technical wiki: silicon, firmware, the community unlock, procedures and open problems. 55 pages.☆75Aug 22, 2026Updated 2 months ago
- A tool to unlobotomize your NVIDIA card!☆836Oct 28, 2026Updated last week
- ☆26Oct 20, 2026Updated 2 weeks ago
- 限制问题区域显存 62906MiB / 65024MiB 支持驱动 610.57.04 ，修改显卡显示名称为NVIDIA Tesla A100☆13Aug 30, 2026Updated 2 months ago
- ☆65Aug 6, 2026Updated 3 months ago
- GPUDirect Storage (GDS) for the NVIDIA CMP 170HX on modern Linux kernels (6.18+). nvidia-fs NVMe registration hooks for the new blk_rq_dm…☆18Aug 19, 2026Updated 2 months ago
- 170hx-pve-gen2-controller☆11Aug 20, 2026Updated 2 months ago
- 双 SM80 / CMP 170HX 的 Qwen3.8-Flash-Next 社区 vLLM：NVIDIA NVFP4、GDS、TEP2、MTP6，支持 1～10 并发，词表与 PCIe 通信优化。中英文部署与可构建源码。☆28Oct 15, 2026Updated 3 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Linux P2P unlock and performance fixes for NVIDIA CMP 170HX☆39Sep 22, 2026Updated last month
- A cmpunlocker fork with working p2p on SYS-4028GR-TRT2☆27Aug 8, 2026Updated 3 months ago
- Qwen3.8-Flash-Next (W4A16) on 2x CMP 170HX: 110 tok/s decode, 7K prefill, 800 tok/s @ 23 concurrent - runs on 38 GB home RAM, no pinned m…☆20Sep 18, 2026Updated last month
- A Pytorch Extention for CMP 170HX☆17Jun 29, 2026Updated 4 months ago
- dsv41-flash-pp5-170hx &pp6 Supports the original (full/unquantized) model. Prefill 7,000 t/s, decode 45-75-125 t/s. dspark. Requires 200 …☆13Updated this week
- Async PLE SSD offload for Qwen3.8 Flash Next on a 64 GiB SM80 GPU: vLLM patch, setup guide, and measured PP/TG results.☆23Sep 24, 2026Updated last month
- Full GLM-5.3 (753B, Int4-Int8Mix) on 4x NVIDIA DGX Spark, vLLM TP4☆23Oct 13, 2026Updated 3 weeks ago
- EXLR8: a DGX Spark tuned quantization format☆14Updated this week
- GLM-5.3-Flash (Z.ai) NVFP4 (LibertAI) + NVFP4 KV, 1M context on 2x DGX Spark GB10 — vLLM TP2 recipe, walls ledger, benchmarks, needle to …☆29Aug 31, 2026Updated 2 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆28Sep 13, 2026Updated last month
- The most comprehensive community resource for the NVIDIA CMP 170HX.☆132Jul 30, 2026Updated 3 months ago
- Userland fan control for NVIDIA DGX Spark, with additive RPM floors, a temperature-based curve, Secure Boot signing, and DKMS support.☆47Oct 29, 2026Updated last week
- Llama-architecture models (SmolLM2 135M, 360M, 1.7B) in Bend 2, token for token against PyTorch, with the shapes in the types☆16Updated this week
- First Int4-Int8Mix quantization of the full GLM-5.3 (743B), served on 4x NVIDIA DGX Spark (GB10) at TP4. Quantizer, verification gates, a…☆20Oct 6, 2026Updated last month
- Fast cross-platform GPU miner for rpow2, 3, and 4 - SHA-256 proof-of-work on any Vulkan-capable GPU (AMD, NVIDIA, Intel, Apple Silicon). …☆12May 8, 2026Updated 6 months ago
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆97Nov 1, 2026Updated last week
- ☆11Jun 5, 2026Updated 5 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆38Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- MiMo-V2.6-Flash-RL on 2x NVIDIA DGX Spark (GB10): vLLM TP2 + DFlash + vision/audio, fp8 KV 300K, four fixes for the stock image, measured…☆47Oct 4, 2026Updated last month
- A fork of jasl/vllm (codex/ds4-sm120-min-enable) with CPU-GPU hybrid inference support for DeepSeek-V4 on SM120+.☆32Sep 10, 2026Updated last month
- Reclaiming the ASRock BC-250 as a real, tunable PC - Cachenetics' open-source firmware liberation + tuning suite.☆23Oct 1, 2026Updated last month
- Timestep-cache acceleration for MiniMax H3 in ComfyUI — open source, cross-platform, ~3x speedup measured☆19Aug 4, 2026Updated 3 months ago
- Strata fork that runs GLM-5.3-Flash (320B-A18B, 157 GB) on one PC: RTX 5090 + 128 GB RAM + NVMe, ~30 tok/s chat. Fork of Niko1221/Strata …☆37Oct 13, 2026Updated 3 weeks ago
- Serve the official Ling-3.0-flash INT4 on one NVIDIA DGX Spark, 38.7 tok/s, faster than the community GGUF. Recipe, watchdog, benchmarks.☆26Aug 29, 2026Updated 2 months ago
- A from-scratch CUDA inference engine for 1-6 DGX Sparks (GB10): GLM-5.3, GLM-5.3-Flash and DeepSeek-V4.1-Flash☆63Updated this week