b10326
tts: account for the vocoder pass in the timings line (#26733) get_output runs the waveform work the pipeline defers to it, from a single trailing window…
Infrastructure 932 stories
Copilot impact dashboard adds a return on investment section
The Copilot impact dashboard now includes a “Potential return on investment” section that connects what you spend on Copilot to the pull request output you get…
Copilot code review effort levels are generally available
Lite and Balanced effort levels for GitHub Copilot code review are now generally available. They let you match the depth of a review to the complexity…
b10322
sycl: coalesce the ssm_conv window loads (#26612) test-backend-ops perf -o SSM_CONV on an Arc Pro B70, interleaved A/B against master, 6 reps, us/run: ne_a=[515,3328,1,1] ne_b=[4,3328,1,1] n_t=512…
b10321
metal : fix NORM/RMS_NORM for row lengths that leave a partial simdgroup (#26708) ggml_metal_op_norm sized the threadgroup with nth = std::min(nth, args.ne00_t), which can leave nth…
Copilot usage metrics API adds agent app activity
Since agent apps arrived on GitHub, teams have been able to run agents from partners like Claude and Codex directly in their GitHub workflows. The Copilot…
b10319
mtmd: fix longest_edge ignoring min/max pixels (#26638) mtmd: fix longest_edge ignoring min/max pixels nits Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI…
b10318
sync : ggml Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU)…
b10313
server: (router) add LRU scheduler (#26572) add lru_sched handle coalescing (req leaves waiting queue) add tests fix stream case address review comments Website: https://llama.app macOS/iOS: macOS…
b10312
server: (router) do not evict busy models (#26567) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS…
b10311
mtmd: stop feeding the text stream again during Qwen3-TTS generation (#26706) The reference implementation has two mutually exclusive prompt layouts. In non streaming mode the prefill…
GitHub Code Quality no longer adds Copilot as a reviewer
Enabling GitHub Code Quality on a repository no longer creates a ruleset that automatically requests a code review from GitHub Copilot on your pull requests. In…
b10310
ggml : add aarch64 HWCAP fallbacks and fix fp16 variant detection (#25554) ggml : add fallback definitions for missing aarch64 HWCAP bits ggml : require HWCAP_ASIMDHP…
b10308
Mitigate crashing issue on Windows MSYS2 UCRT64 environment (GCC 16.1.0) (#26555) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS…
b10307
sycl: fix UE4M3 parsing (#25608) The NVFP4 quantization format stores a scaling factor for every group of 16 weights, packed into a single UE4M3 byte. The…
b10306
sycl: *glu flat path (#26354) tests: add SWIGLU perf cases perf mode had no GLU coverage. Adds SWIGLU at 17408 columns, 512 and 2048 tokens, f16…
b10305
sycl : Support DSv4 OPs: LIGHTNING_INDEXER,DSV4_HC_COMB,DSV4_HC_POST,DSV4_HC_PRE (#26568) support DSv4 OPs: LIGHTNING_INDEXER,DSV4_HC_COMB,DSV4_HC_POST,DSV4_HC_PREwq update ops.md fix format issue Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon…
b10303
sycl : fix error Error OP FLASH_ATTN_EXT on arc770 (#26441) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel…
b10301
cuda: fix warnings for unused variable/function (#26688) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework…
b10299
metal : avoid threadgroup matrix array instantiation in kernel_lightning_indexer (#26646) In MSL, declaring an array of matrix types like threadgroup half4x4 causes a 'no matching constructor'…
MCP allowlists in enterprise managed settings
Enterprise owners can now centrally control which Model Context Protocol (MCP) servers GitHub Copilot clients are allowed to run by using the new allowedMcpServers and deniedMcpServers…
b10298
mtmd: add chunk save/load function (#26645) mtmd: add chunk save/load function nits add tests rn _MAX --> _COUNT Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS…
Kimi K3 is now available in GitHub Copilot
Kimi K3, an open-weight model, is now generally available in GitHub Copilot. The model shows frontier-level abilities on agentic coding with highly cost-effective pricing. Kimi K3…
b10297
server: fix empty response for /cors-proxy (#26656) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework…