openbmb/VoxCPM2
Text-to-Speech • Updated • 188k • 1.32k
Muratcan Laloğlu
muratcanlaloglu
·
AI & ML interests
None yet
Recent Activity
liked a model about 1 month ago
openbmb/VoxCPM2 liked a dataset about 2 months ago
merve/vlm_test_images reacted to Hellohal2064's post with 🔥 4 months ago
🚀 Excited to share: The vLLM container for NVIDIA DGX Spark!
I've been working on getting vLLM to run natively on the new DGX Spark with its GB10 Blackwell GPU (SM121 architecture). The results? 2.5x faster inference compared to llama.cpp!
📊 Performance Highlights:
• Qwen3-Coder-30B: 44 tok/s (vs 21 tok/s with llama.cpp)
• Qwen3-Next-80B: 45 tok/s (vs 18 tok/s with llama.cpp)
🔧 Technical Challenges Solved:
• Built PyTorch nightly with CUDA 13.1 + SM121 support
• Patched vLLM for Blackwell architecture
• Created custom MoE expert configs for GB10
• Implemented TRITON_ATTN backend workaround
📦 Available now:
• Docker Hub: docker pull hellohal2064/vllm-dgx-spark-gb10:latest
• HuggingFace: huggingface.co/Hellohal2064/vllm-dgx-spark-gb10
The DGX Spark's 119GB unified memory opens up possibilities for running massive models locally. Happy to connect with others working on the DGX Spark Blackwell!Organizations
None yet
liked a
model about 1 month ago
liked a
dataset about 2 months ago
reacted to Hellohal2064's post with 🔥 4 months ago
Post
1710
🚀 Excited to share: The vLLM container for NVIDIA DGX Spark!
I've been working on getting vLLM to run natively on the new DGX Spark with its GB10 Blackwell GPU (SM121 architecture). The results? 2.5x faster inference compared to llama.cpp!
📊 Performance Highlights:
• Qwen3-Coder-30B: 44 tok/s (vs 21 tok/s with llama.cpp)
• Qwen3-Next-80B: 45 tok/s (vs 18 tok/s with llama.cpp)
🔧 Technical Challenges Solved:
• Built PyTorch nightly with CUDA 13.1 + SM121 support
• Patched vLLM for Blackwell architecture
• Created custom MoE expert configs for GB10
• Implemented TRITON_ATTN backend workaround
📦 Available now:
• Docker Hub: docker pull hellohal2064/vllm-dgx-spark-gb10:latest
• HuggingFace: huggingface.co/Hellohal2064/vllm-dgx-spark-gb10
The DGX Spark's 119GB unified memory opens up possibilities for running massive models locally. Happy to connect with others working on the DGX Spark Blackwell!
I've been working on getting vLLM to run natively on the new DGX Spark with its GB10 Blackwell GPU (SM121 architecture). The results? 2.5x faster inference compared to llama.cpp!
📊 Performance Highlights:
• Qwen3-Coder-30B: 44 tok/s (vs 21 tok/s with llama.cpp)
• Qwen3-Next-80B: 45 tok/s (vs 18 tok/s with llama.cpp)
🔧 Technical Challenges Solved:
• Built PyTorch nightly with CUDA 13.1 + SM121 support
• Patched vLLM for Blackwell architecture
• Created custom MoE expert configs for GB10
• Implemented TRITON_ATTN backend workaround
📦 Available now:
• Docker Hub: docker pull hellohal2064/vllm-dgx-spark-gb10:latest
• HuggingFace: huggingface.co/Hellohal2064/vllm-dgx-spark-gb10
The DGX Spark's 119GB unified memory opens up possibilities for running massive models locally. Happy to connect with others working on the DGX Spark Blackwell!
- 4 replies
liked 2
models 5 months ago
liked a
Space 6 months ago
liked 6
models 6 months ago
thelamapi/next-4b
Image-Text-to-Text • 4B • Updated • 177 • 8
thelamapi/next-1b
Text Generation • 1.0B • Updated • 601 • • 27
vafipas663/Qwen-Edit-2509-Upscale-LoRA
Image-to-Image • Updated • 12.9k • • 226
cyankiwi/Magistral-Small-2509-AWQ-4bit
5B • Updated • 271 • 3
jeffcookio/Mistral-Small-3.2-24B-Instruct-2506-awq-sym
5B • Updated • 10.1k • 12
unsloth/Mistral-Small-3.2-24B-Instruct-2506-bnb-4bit
Image-Text-to-Text • 25B • Updated • 304k • 10
liked 2
models 7 months ago
liked a
model 8 months ago
liked a
model 9 months ago
liked 3
models 10 months ago
liked a
model about 1 year ago
