☆37Apr 26, 2026Updated 6 months ago
Alternatives and similar repositories for deepseek-v4-flash-sm120
Users that are interested in deepseek-v4-flash-sm120 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆17Oct 20, 2026Updated 3 weeks ago
- NVFP4 KV cache for vLLM on SM120 (RTX PRO 6000) via FlashInfer FA2 explicit-SF-stride patch — ~1.5x fp8 pool at ~95-104% speed☆20Jun 5, 2026Updated 5 months ago
- Truthful scheduler-step and streaming visualization for local LLM inference☆36Sep 6, 2026Updated 2 months ago
- 使用cuda实现类似sahi库的切图☆13Jul 21, 2026Updated 3 months ago
- MiniMax-M3 (MXFP4, MSA) serving on SM120 (RTX PRO 6000 Blackwell) — patched vLLM image + launch recipe, 192K context☆23Jun 15, 2026Updated 5 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆23Aug 20, 2025Updated last year
- The agent that grows with you☆14Oct 14, 2026Updated last month
- Docker images for LLM inference (SGLang + vLLM) on NVIDIA Blackwell GPUs (SM120, CUDA 13.2)☆100Oct 20, 2026Updated 3 weeks ago
- Serve EXL3 (ExLlamaV3 trellis) quantized models on vLLM fork runtimes — any architecture, mixed per-layer bitrates, composable with sourc…☆27Nov 5, 2026Updated last week
- RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink☆18Updated this week
- Qwen3.5-Thor — High-performance BF16/NVFP4 inference engine for Qwen3.5 model family on NVIDIA Jetson AGX Thor (SM110a Blackwell). C++17/…☆13Apr 2, 2026Updated 7 months ago
- DeepSeek-V4-Flash W4A16-FP8 quantization on 8x H200 — patches, recipe, mission report☆13Sep 26, 2026Updated last month
- object detection with lidar point cloud, with real-time performance. This is a simplified version of SECOND project by Yan Yan☆17Nov 5, 2020Updated 6 years ago
- Work with Pi☆15Feb 9, 2026Updated 9 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Vault-backed issue tracker. Issues as Obsidian-compatible markdown files. No database server. No size limits. Git-native. Built on vlt.☆10Jul 22, 2026Updated 3 months ago
- DeepSeek V4.1 Flash on 4x RTX PRO 6000 Blackwell: native weights, DSpark, vision, NVMe or locked RAM Engram offload.☆91Oct 17, 2026Updated 3 weeks ago
- SGLang for GLM-5.3-Flash on two or four RTX PRO 6000 Blackwell GPUs (SM120), with TP2 W4A16 and TP4 NVIDIA NVFP4 profiles.☆48Oct 11, 2026Updated last month
- Validated GLM-5.3 Flash recipe for 2x NVIDIA RTX PRO 6000 Blackwell 96GB: 262K context, EXL3/TR3, adaptive MTP, tools, and vision.☆63Sep 20, 2026Updated last month
- study of cutlass☆22Nov 10, 2024Updated 2 years ago
- Lightweight tools for quick and easy LLM demo's☆28Sep 22, 2024Updated 2 years ago
- Archived: b12x development has moved to FlashInfer. See README for migration and PR-porting guidance.☆269Oct 6, 2026Updated last month
- Fast, standalone CLI for Obsidian vault operations. No Electron, no app dependency, no network calls.☆11Jun 12, 2026Updated 5 months ago
- ☆21Oct 21, 2026Updated 3 weeks 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.
- Tutorials for the PIQM-2023 Advanced School☆11Sep 29, 2026Updated last month
- Node Equivariant Message Passing Neural Network☆12Nov 4, 2026Updated last week
- give me a toml configuration file, I'll give you export MY_ENV=foo☆10Jul 6, 2018Updated 8 years ago
- Breakable CUDA graph capture for PyTorch - capture compatible regions as CUDA graphs while running incompatible operations eagerly betwee…☆30Oct 8, 2026Updated last month
- A demonstrative example of running SGLang Diffusion with DP router☆26Mar 15, 2026Updated 8 months ago
- Qwen 3.8 Flash NVFP4 with PLE NVFP4 quantized to run on a single DGX Spark☆15Aug 28, 2026Updated 2 months ago
- Notification integration for SimpleX messenger☆23Oct 19, 2026Updated 3 weeks ago
- fake CUTLASS to get peformance☆26Apr 28, 2026Updated 6 months ago
- ☆64Sep 27, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- FLA but cuTile☆27Apr 17, 2026Updated 6 months ago
- ☆22May 10, 2026Updated 6 months ago
- ⚠️ Moved to https://github.com/ogulcancelik/pi-extensions/tree/main/packages/pi-web-browse☆18Mar 17, 2026Updated 7 months ago
- ☆24May 9, 2026Updated 6 months ago
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 9 months ago
- NCU-driven iterative optimization workflow for CUDA/CUTLASS/Triton/CuTe DSL kernels.☆25Apr 10, 2026Updated 7 months ago
- ComfyUI nodes for Mistral's Voxtral-4B text-to-speech model with direct PyTorch inference. Supports 20 preset voices across 9 languages o…☆13Aug 23, 2026Updated 2 months ago
Are these results useful?