b10357
opencl: transpose the K tile in local memory for FA prefill kernels (#26428) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled)…
Infrastructure 932 stories
b10362: tests : disable backend sampler hip multi output (#26878)
test-backend-sampler: skip multi_output_sampling_chain on HIP The new multi_output_sampling_chain test uses top_k, whose backend probs path needs CUB (unavailable on HIP), so sampled_probs is null and the…
b10356
ci : target ROCm 7.14 for build and release (#25775) Switch ROCm from 7.2.1 to 7.14 ROCm 7.14 is the first production release using TheRock build…
b10355
llama : support multi-output backend sampling (#25532) Enable backend sampling with token speculation Clamp the mask sum before converting it into the sampled index Add a…
b10354
ggml-cpu : fix CPU affinity mask being ignored on Android (#26838) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS…
b10353
ggml : require contiguous src for ROLL on CUDA and Metal (#25928) ggml_roll only asserts nb[0] == ggml_type_size, so a permuted src is a valid input,…
b10344
model: add MTP support for Nemotron model (#26725) model: add MTP support for Nemotron Nano model model: add mtp_flags for nemotron model address review comments Website:…
b10343
vendor : update cpp-httplib to 0.53.0 (#26821) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework…
Copilot on web expands conversation controls
We’ve made improvements to Copilot Chat on github.com that make it easier to use. These include easier access to your recent conversations in chat, the ability…
Run Local Agentic AI Workflows with Meta’s Muse Glimmer on NVIDIA
Meta returns to the open source ecosystem with the release of Muse Glimmer, a 30B open-weight dense model with a 120K+ context window built for local…
b10342
model : Granite-Switch Architecture (#25107) granite-switch: add llama.cpp backend (POC, CPU) New "granite-switch" architecture: a dense, all-attention Granite-4.1 model with N embedded LoRA adapters selected per-token…
b10338
model-saver : fix expert shared/chunk FFN length key clobber (#26693) The saver called add_kv with LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH twice, the second time passing n_ff_chexp. gguf_set_val_u32 removes-then-appends, so the…
b10336
ggml-webgpu : refactor several wgsl files and simplify flash_attn wgsl. (#26134) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS…
Muse Glimmer from Meta Superintelligence Labs is now available on Ollama
Meta's Muse Glimmer, the first open model released by Meta Superintelligence Labs, is now available on Ollama. Muse Glimmer is a 30B multimodal model released under…
b10335
ui: degrade the working directory picker when file search is off (#26…
b10333
ggml-cpu : fix missing Q5_0 dispatch in SpaceMiT backend (#26792) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel…
b10332
ci: rm GGML_HIP_ROCWMMA_FATTN (#26760) Signed-off-by: Aaron Teo aaron.teo1@ibm.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS…
b10331
server: report the isolate working directory from get_info (#26773) server: report the isolate working directory from get_info Without an explicit cwd, get_info fell back to the…
b10330
CUDA: fuse rms_norm + mul + rope (+ view + set_rows) (#26767) CUDA: fuse rms_norm + mul + rope (+ view + set_rows) tests: add broadcast…
b10329
server, ui: only offer a working directory when a tool reads it (#26762) The working directory chip showed up as soon as the server exposed any…
b10328
server: add initial tool isolation support (via docker) (#26507) server: add initial tool isolation support (via docker) add docs adapt get_info py: fix type check cont…
Firebird Launches CIS Region’s Largest AI Factory in Armenia
The global buildout of AI infrastructure reached a new milestone today — Firebird, an emerging AI cloud, launched the CIS region’s largest AI factory in Armenia,…
b10327
CUDA: fix thread/block count in quantized cpy kernel launches (#26731) CUDA: fix thread/block count in quantized cpy kernel launches tests: add uneven block count cpy case…
GitHub Copilot weekly releases — August 3
This week’s updates across GitHub Copilot in the desktop app, CLI, and VS Code help you resume and organize work, review changes, and ask questions without…