TensorSharp
PulseAugur coverage of TensorSharp — every cluster mentioning TensorSharp across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Qwen3.8 27B: Six inference engines benchmarked on RTX 5090
A comparison of six inference engines—TensorSharp, llama.cpp, vLLM, SGLang, velox-inferer, and NInfer—running the Qwen3.8 27B model on a single RTX 5090 GPU revealed varying performance across different tasks. NInfer ex…
-
TensorSharp adds MiniMax-M3.1-Flash support, outperforming llama.cpp on long prompts
TensorSharp, a new inference engine, has added support for the recently released MiniMax-M3.1-Flash model. Benchmarks conducted on eight NVIDIA A40 GPUs show TensorSharp significantly outperforming a tested llama.cpp br…
-
Muse Spark 816B runs on 10 A40 GPUs, TensorSharp outperforms llama.cpp
A user has successfully run the Muse Spark 816B model, which has 42 billion active parameters, across ten NVIDIA A40 GPUs. Benchmarks comparing the TensorSharp inference engine with llama.cpp revealed significant perfor…
-
TensorSharp adds local video generation and editing studio
A developer has integrated a local video studio into TensorSharp, an open-source inference engine and agent runtime. This new feature allows users to generate video from still images using models like LTX 2.5 Distilled,…
-
Qwen releases Qwen-Image-2.1-Turbo for accelerated image generation
The Qwen/Qwen-Image-2.1-Turbo model has been released, offering accelerated text-to-image generation and editing capabilities with a reduced number of denoising steps. This model, built on the Qwen-Image-2.1 architectur…
-
Qwen3.8 Flash Next model optimized for local inference on diverse hardware
The Qwen3.8 Flash Next model is being optimized for local inference across various hardware configurations. One user achieved 400 tokens/sec on an RTX 6000 with a fork of NInfer, while another demonstrated running the m…
-
New C#/.NET engine TensorSharp rivals llama.cpp performance
TensorSharp, a new inference engine for GGUF models, has emerged as a pure C#/.NET alternative to established C/C++ engines like llama.cpp. Developed by zhongkaifu, it offers broad model and backend support, including C…
-
DeepSeek V4 Flash 0731 sees significant speedup with DSpark on TensorSharp
A new benchmark result highlights the performance gains of DeepSeek V4 Flash 0731 when utilizing DSpark with the TensorSharp inference engine. Across various generation tasks, including short and long outputs, follow-up…
-
TensorSharp LLM Inference Engine Benchmarked Against llama.cpp
TensorSharp, a new open-source LLM inference engine, has been released with performance benchmarks comparing it against llama.cpp. The engine supports various models including Gemma4 and Qwen3.6, and offers compatibilit…
-
TensorSharp adds Qwen Image Edit 2511 support, benchmarks faster than stable-diffusion.cpp
TensorSharp, an open-source LLM inference engine, now supports image editing and generation using Qwen Image Edit 2511 models with LoRA. Benchmarks indicate that TensorSharp outperforms stable-diffusion.cpp in several k…
-
TensorSharp adds Vulkan backend for LLM inference, benchmarks against llama.cpp
TensorSharp, an open-source LLM inference engine, has released an initial version of its GGML Vulkan backend, aiming to improve performance on GPUs. The update was tested successfully on Nvidia and Intel GPUs, with the …