b10153
model: Add support for Nanbeige4.2 (#25994) support nanbeige4.2 model fix fix flake8 Lint check fix loop bound check and drop redundant head_dim Co-authored-by: root lizongqiang@kanzhun.com Website:…
Infrastructure 944 stories
b10152
fit : count nextn (MTP) blocks in n_gpu_layers so front layers stay on GPU (#26177) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64,…
b10151
sycl(build): parallelize ocloc invocations (#25903) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu…
b10150
ggml : adjust logic for offloading ops to weight's backend (#25832) ggml : adjust logic for offloading ops to weight's backend llama : dsv4 graph fixes…
b10149
tests : remove unnecessary sync in test-save-load-state (#26166) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS…
b10148
common: fix explicit -md precedence over draft sidecar resolution (#26165) common: fix explicit -md precedence over draft sidecar resolution Follow-up of #25955, an explicit --model-draft file…
b10146
ggml-cpu: Enable BF16 tiled gemm optimization on PowerPC (#26068) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)…
b10145
args: add -lm mlock where it mlocks but doesnt mmap (#26135) arg: add -lm mlock where it mlocks but doesnt mmap Signed-off-by: Aaron Teo aaron.teo1@ibm.com docs:…
Industry Leaders Unite in Open Secure AI Alliance for AI Safety and Security
Open source software is a critical pillar of the global economy. It underpins cloud computing, financial services, manufacturing, telecommunications, government and internet services by making technology…
Six Agent Harness Capabilities for Higher Model Performance
Building a great AI agent isn’t just about choosing the right models. The harness is the architecture surrounding the model. How it renders context, executes...
b10144
server + ui: fix stream routes for model names containing a slash (#26137) server + ui: refactor resumable stream routes to query string conv_id The conversation…
NVIDIA Harnesses Vera CPU to Speed Up Design of Next-Generation CPUs and GPUs
The complexity of modern chip design continues to grow as engineering teams work to develop increasingly sophisticated CPUs, GPUs and AI systems. To help meet that…
Advancing Semiconductor Innovation Across Materials Engineering and Manufacturing
As AI workloads increase, explosive compute demand is pushing the semiconductor industry to meet unprecedented performance targets. Even small delays can have...
NVIDIA Nemotron 3 Ultra Leads Open Models on Accuracy and Efficiency in Agentic RTL Coding
Modern chip design is increasingly limited by engineering time. Register transfer level (RTL) development and verification require specialized hardware...
b10143: ui: Fix symbolic math tool JS sandbox prompt (#26131)
Update sandbox.ts Update sandbox.ts Update sandbox.ts Update sandbox.ts Revise nerdamer description in sandbox constants Updated NERDAMER_DESCRIPTION to clarify usage and warnings.
b10142
mtmd: Add Vision Support for Minimax-M3 (#25113) Add preliminary MiniMax-M3 support Text-only port that re-uses existing components: MiniMax-M2 style GQA with per-head QK-norm and partial rotary,…
b10141
mtmd: fix android build (#26150) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu…
b10133
ui: fix context gauge card regressions and land at the conversation e…
Kimi K3 vs GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing
We ran 904 DeepSWE rollouts on Kimi K3 and GPT-5.6 Sol. Sol leads pass@1; Kimi K3 wins pass@4 at 2.8x the solves per dollar, and routing…
b10121: ui: reduce per-token render cost when streaming (#26053)
performance harness - the empirical root Assisted-by: Claude Opus 4.8 210.36ms -> 2.67ms per streamed token Assisted-by: Claude Opus 4.8 11.58ms -> 0.62ms per streamed token…
ModelExpress: Distributing Model Artifacts at the Speed of Light
Every byte moved has a cost. As model checkpoints grow to hundreds of gigabytes or even a terabyte, that cost adds up quickly. To make things…
Claude Opus 5 is now available in GitHub Copilot
Claude Opus 5, Anthropic’s newest Opus model, is now available in GitHub Copilot. It is designed for complex, long-running coding tasks that require careful reasoning, effective…
b10107
hexagon: fix Windows crash when op_poll is enabled (#26029) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)…
b10106
CUDA: fix external compilation of q1_0 MMQ (#25778) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS…