b9915
ggml : add support for CPU f16->f16 GGML_OP_SET_ROWS (#25344) ggml : add support for CPU f16->f16 GGML_OP_SET_ROWS ggml : add missing type checks in f16 GGML_OP_SET_ROWS…
Infrastructure 951 stories
b9914
opencl: fix potential crash in aos reconstruct (#25383) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux:…
b9913
Add Q2_0 quantization: type definition and CPU backend (#24448) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework…
b9912
spec : fix naming, spacing (#25410) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64…
b9911
CUDA: Fuse MMVQ post-scale for NVFP4 (#24481) CUDA: Fuse MMVQ for NVFP4 and BS 1 TODO: Add tests to test-backend-ops (did verify correctness manually for one…
b9917: fix: OOB reads in UGM tokenizer (precompiled_charsmap handling) (#18750)
fix: OOB reads in UGM tokenizer (precompiled_charsmap handling) Validate minimum size (4 bytes) before reading xcda_blob_size Use strnlen with bounds check instead of unsafe strlen Both…
Add review cycles and time to adoption phases in the usage API
The Copilot usage metrics API now reports two additional code-review velocity metrics for each AI adoption phase, extending the adoption phase cohorts fields available in the…
b9910
server : fix draft model fit vs load inconsistency (#25056) fix: draft model fit vs load inconsistency refactor(server): unify draft/mtp parameter initialization, model, and context load…
b9909
server : add timings and progress to /responses API stream (#25348) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)…
Codex as agent provider and agentic enhancements in JetBrains IDEs
This update brings Codex as a new agent provider in public preview, expands the Customizations editor with Hooks support and richer MCP server management, and introduces…
b9908
server: enforce prompt cache RAM limit (#25070) Before this commit, --cache-ram was not a hard limit: The cache always kept at least one entry, even if…
b9907
common : add missing include in common.h (#25220) Signed-off-by: zhangrunda zhangrunda1234@outlook.com macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)…
b9906
ggml-hip : add -fno-finite-math-only alongside -ffast-math (#25373) -ffast-math implies -ffinite-math-only under ROCm/clang 22, which disables INFINITY/NaN and triggers -Wnan-infinity-disabled (errors under -Werror in CI). Re-enable infinity…
b9905
llama: fix quantized kv-cache for dsv4 (#25202) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu…
Kimi K2.7 now available for Copilot Business and Enterprise
On July 1, 2026, we announced Kimi K2.7 would be available to Copilot Pro, Pro+, and Max plans. The model is now additionally available on Copilot…
Introducing Grok 4.5
Our most intelligent model and the first we've built for more than software engineering.
Open, convenient and predictable: Introducing Provisioned Throughput
Provisioned Throughput gives you reserved inference capacity for frontier open models like MiniMax M3 and GLM-5.2. Token-based pricing, a 99% uptime SLA, and up to 90%…
b9904
[SYCL] fix unsupported UT cases of CONT & CPY (#25231) fix unsupported UT cases of CONT & CPY update ops.md rm unused head file macOS/iOS: macOS…
b9902
[SYCL] support OP cross_entropy_loss, cross_entropy_loss_back (#25236) support OP cross_entropy_loss, cross_entropy_loss_back correct format issue macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS…
Per-user budgets for cost centers in the billing UI
Enterprise admins can now create cost center user-level budgets directly in the billing UI where you manage cost centers and budgets. This feature is available for…
Develop Humanoid Robot Policies End-to-End with NVIDIA Isaac GR00T
As more teams move from humanoid robot bring-up to task-specific skill development, the need for repeatable development workflows is growing. Building humanoids...
Building an Analysis AI Agent for Industrial Alarm Management with NVIDIA Nemotron
Industrial machinery generates more alarms than technicians can triage. For each important alarm requiring follow-up, the technician pulls historical context,...
Maximize Spectral Efficiency with AI-Native RAN and NVIDIA AI Aerial
Spectrum is one of the most valuable assets in wireless communications. Over the last 30 years, telecom operators in the US have spent more than $240B…
b9901
sycl : set K_QUANTS_PER_ITERATION to 1 on DMMV path (#25063) sycl: add supported types to ggml_sycl_supports_reorder_dmmv The reordered feature is implemented in ggml_sycl_op_dequantize_mul_mat_vec, but gated by…