Similar to This
Previous

Support rectangular gated delta net states by shan18 · Pull Request #32765 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/32765

vulkan : support non-contiguous src in SCALE by Revertron · Pull Request #32735 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/32735

Inkling 2 Mini by pcuenca · Pull Request #32694 · ggml-org/llama.cpp: LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account ...
github.com/ggml-org/llama.cpp/pull/32694

chat : refactor gemma4 to build loose schema rules and clean up by aldehir · Pull Request #31915 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/31915
feat: external PLE file loading by pwilkin · Pull Request #31185 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/31185

mtmd: support MageVL-Cowork model by ngxson · Pull Request #31819 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/31819

moe-cache : LRFU/MQ-like hybrid cache, ClassLRU by sanmai · Pull Request #31233 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/31233
Add MiniMax-M3 (MSA: MiniMax Sparse Attention) support by timkhronos · Pull Request #24908 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/24908

kv-cache : avoid kv cells copies by ggerganov · Pull Request #24277 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/24277
![[PoC] server: support requantizing kv cache by wadealexc · Pull Request ...](https://external-preview.redd.it/Uwg2OuKYL_cyUNuDl_QbKE8QLJOJXgBPbR0_Jgg2eAo.png?width=320&crop=smart&auto=webp&s=e349140f70c63a9307fcb53420c133424145284f)
[PoC] server: support requantizing kv cache by wadealexc · Pull Request #24134 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/24134
Asymmetric KV q8/q4 cache to preserve precision while reducing memory usage · ggml-org/llama.cpp · Discussion #23470
github.com/ggml-org/llama.cpp/discussions/23470
GitHub - ParmesanParty/llama.cpp: Specialized fork for (relatively) fast single-GPU inference (in CUDA) using large MoE models that don't fit fully into ...
github.com/ParmesanParty/llama.cpp

kv-cache : support attention rotation for heterogeneous iSWA by ggerganov · Pull Request #21513 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/21513

(revert) kv-cache : do not quantize SWA KV cache by ggerganov · Pull Request #21332 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/21332

llama : rotate activations for better quantization by ggerganov · Pull Request #21038 · ggml-org/llama.cpp
github.com/ggml-org/llama.cpp/pull/21038
Next

