github

GitHub API

9 events on 2026-04-30role: entity7d historyaccess: keyless

Keeps: repo, release, stars delta

← prev day2026-04-30next day →all history

2026-04-30ggerganov/llama.cpp b8992: b8992
<details open> Update llama-mmap to use ftello/fseeko (#22497) * Update llama-mmap to work with 32-bit wasm and >2GB models * Update to gguf.cpp style </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b8992/llam
github:ggerganov/llama.cpp
2026-04-30ggerganov/llama.cpp b8991: b8991
<details open> common : check for null getpwuid in hf-cache (#22550) Signed-off-by: Adrien Gallouët <angt@huggingface.co> </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b8991/llama-b8991-bin-macos-arm64.tar.gz
github:ggerganov/llama.cpp
2026-04-30ggerganov/llama.cpp b8989: b8989
<details open> spec: fix argument typo (#22552) </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b8989/llama-b8989-bin-macos-arm64.tar.gz) - [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/ggml
github:ggerganov/llama.cpp
2026-04-30ggerganov/llama.cpp b8990: b8990
<details open> vulkan: add get/set tensor 2d functions (#22514) * vulkan: add get/set_tensor_2d functions * fix backend interface comments * Update ggml/src/ggml-metal/ggml-metal.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> </details> **macOS/iOS:** -
github:ggerganov/llama.cpp
2026-04-30ggerganov/llama.cpp b8987: b8987
<details open> vendor : update cpp-httplib to 0.43.2 (#22548) Signed-off-by: Adrien Gallouët <angt@huggingface.co> </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b8987/llama-b8987-bin-macos-arm64.tar.gz) - [ma
github:ggerganov/llama.cpp
2026-04-30ggerganov/llama.cpp b8986: b8986
<details open> CUDA: fix tile FA kernel on Pascal (#22541) </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b8986/llama-b8986-bin-macos-arm64.tar.gz) - [macOS Apple Silicon (arm64, KleidiAI enabled)](https://gith
github:ggerganov/llama.cpp
2026-04-30ggerganov/llama.cpp b8984: b8984
<details open> add fast matmul iquants (#22504) </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b8984/llama-b8984-bin-macos-arm64.tar.gz) - [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/ggml
github:ggerganov/llama.cpp
2026-04-30ggerganov/llama.cpp b8983: b8983
<details open> spec : fix draft model checkpoints (#22521) * spec : fix draft model checkpoints * cont : clean-up * cont : gate the ngram-mod reset warning behind verbose flag </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/re
github:ggerganov/llama.cpp
2026-04-30ggerganov/llama.cpp b8982: b8982
<details open> spec : fix vocab compat checks in spec example (#22426) * port #22358 PR to examples/speculative/speculative.cpp * use vocab_[tgt,dft] instead of ctx_[tgt,dft] when logging on draft model / target model vocabulary mismatch Co-authored-by: Petros Sideris <petro
github:ggerganov/llama.cpp