| 2026-07-17 |
Todd Malsbary | sycl: fix row calculation when K_QUANTS_PER_ITERATION... |
commit | commitdiff | tree |
| 2026-07-17 |
Gezahegne | opencl: add ABS op (#25115) |
commit | commitdiff | tree |
| 2026-07-16 |
Hongqiang Wang | opencl: loads quants as uint for q4_K and q5_K flat... |
commit | commitdiff | tree |
| 2026-07-16 |
akleine | docs: added a note about using OpenCl with Adreno 810... |
commit | commitdiff | tree |
| 2026-07-16 |
Aman Gupta | DeepseekV4: Add fused hyper-connection ops (#25585) |
commit | commitdiff | tree |
| 2026-07-16 |
Max Krasnyansky | hexagon: L2 cache handling rework (dirty bit tracking... |
commit | commitdiff | tree |
| 2026-07-16 |
Rajendra Matcha | kleidiai: Add SME vs SME2 distinction in kernel dispatc... |
commit | commitdiff | tree |
| 2026-07-16 |
Ruben Ortlam | vulkan: when using transfer queue for async copies... |
commit | commitdiff | tree |
| 2026-07-16 |
Khashayar Ghafouri | conversion: accept BitNetForCausalLM architecture name... |
commit | commitdiff | tree |
| 2026-07-16 |
Johannes Gäßler | TP: fix Phi3, Bert, Plamo2/3, ChatGLM (#25536) |
commit | commitdiff | tree |
| 2026-07-16 |
Alessandro... | vendor: update BoringSSL to 0.20260713.0 (#25624) |
commit | commitdiff | tree |
| 2026-07-16 |
Aman Gupta | tests: actually exercise `test-recurrent-state-rollback... |
commit | commitdiff | tree |
| 2026-07-16 |
Chipmunk | server : allow text-only slot save/restore with mtmd... |
commit | commitdiff | tree |
| 2026-07-16 |
Ruixiang Wang | convert : fix dflash target tokenizer mismatch during... |
commit | commitdiff | tree |
| 2026-07-16 |
Anav Prasad | CUDA: Support CUDA Virtual Devices (#25228) |
commit | commitdiff | tree |
| 2026-07-16 |
Alexander Heisler | Enable CUDA graphs on volta+turing (#25749) |
commit | commitdiff | tree |
| 2026-07-16 |
Sebastian Dröge | server: Ignore empty / non-existing `Origin` headers... |
commit | commitdiff | tree |
| 2026-07-16 |
liminfei-amd | ggml-cuda : restore prop.integrated on HIP builds ... |
commit | commitdiff | tree |
| 2026-07-16 |
Pranesh Gonegandla | CUDA: dedup MoE gate/up activation quantization (#25441) |
commit | commitdiff | tree |
| 2026-07-16 |
Georgi Gerganov | ci : add official website link to release notes (#25728) |
commit | commitdiff | tree |
| 2026-07-16 |
Georgi Gerganov | quant : allow using manual tensor types with --pure... |
commit | commitdiff | tree |
| 2026-07-16 |
Hongqiang Wang | opencl: disable FA and MoE weights repack to work aroun... |
commit | commitdiff | tree |
| 2026-07-16 |
David Friehs | cuda: extract Q1_0 elements via __byte_perm (#25628) |
commit | commitdiff | tree |
| 2026-07-15 |
Hongqiang Wang | opencl: exclude some moe kernels on Adreno a7x (#25698) |
commit | commitdiff | tree |
| 2026-07-15 |
Aleksander... | ui: Agentic Content UX improvements (#25450) |
commit | commitdiff | tree |
| 2026-07-15 |
fairydreaming | cuda : CUDA GGML_OP_LIGHTNING_INDEXER implementation... |
commit | commitdiff | tree |
| 2026-07-15 |
Adrien Gallouët | tokenize : drop --stdin mutual-exclusion check (#25672) |
commit | commitdiff | tree |
| 2026-07-15 |
Hongqiang Wang | opencl: fix two issues on flash attention for Adreno... |
commit | commitdiff | tree |
| 2026-07-15 |
leonardHONG | CUDA: tighter MMQ src1 buffer size for native fp4 ... |
commit | commitdiff | tree |
| 2026-07-15 |
Gaurav Garg | Fix crash with draft-simple (#25720) |
commit | commitdiff | tree |
| 2026-07-15 |
Pascal | server: fix read_file append_loc space breaking edit_fi... |
commit | commitdiff | tree |
| 2026-07-15 |
Pascal | ui: fix thinking menu never appearing in single-model... |
commit | commitdiff | tree |
| 2026-07-15 |
fairydreaming | cuda : relax tensor contiguity requirements for quantiz... |
commit | commitdiff | tree |
| 2026-07-15 |
Georgi Gerganov | ci : add HF_TOKEN to self-hosted workflows (#25706) |
commit | commitdiff | tree |
| 2026-07-15 |
Pascal | metal: fuse snake activation (mul, sin, sqr, mul, add... |
commit | commitdiff | tree |
| 2026-07-15 |
Michael Lamothe | ggml: add f16 out_prod support for CPU and out_prod... |
commit | commitdiff | tree |
| 2026-07-15 |
Aman Gupta | DeepseekV4: reduce graph splits (#25702) |
commit | commitdiff | tree |
| 2026-07-15 |
Neo Zhang | sycl : fix get_rows Q2_K, Q4_K, Q5_K (#25656) |
commit | commitdiff | tree |
| 2026-07-15 |
Neo Zhang | sycl : support kernel type fp16 for conv2d_dw (#25653) |
commit | commitdiff | tree |
| 2026-07-15 |
Andrew Smith | sycl : implement xielu op (#25550) |
commit | commitdiff | tree |
| 2026-07-15 |
Francois Dugast | sycl: Increase minimum buffer size for USM system alloc... |
commit | commitdiff | tree |
| 2026-07-15 |
hmscider | [SYCL] Flash Attention with XMX engine via oneDNN ... |
commit | commitdiff | tree |
| 2026-07-15 |
Hongqiang Wang | opencl: do not use `clCreateBufferWithProperties` when... |
commit | commitdiff | tree |
| 2026-07-14 |
Hongqiang Wang | opencl: handle OOB write in noshuffle GEMV kernels... |
commit | commitdiff | tree |
| 2026-07-14 |
Hongqiang Wang | opencl: avoid the vec path in GEMV for unaligned row... |
commit | commitdiff | tree |
| 2026-07-14 |
Chyan | hexagon: fix hmx-queue signal enum-narrowing problem... |
commit | commitdiff | tree |
| 2026-07-14 |
Georgi Gerganov | server : refactor prompt cache state ownership (#25649) |
commit | commitdiff | tree |
| 2026-07-14 |
Xuan-Son Nguyen | server: add --cors-* options (#25655) |
commit | commitdiff | tree |
| 2026-07-14 |
Bill Sideris | ui: Fix spacing in tool-call request (#25634) |
commit | commitdiff | tree |
| 2026-07-14 |
Emanuil Rusev | webui: parse effective-parameter sizes (E2B, E4B) as... |
commit | commitdiff | tree |
| 2026-07-14 |
Hongqiang Wang | opencl: fix a dp4a bug for devices where cl_khr_integer... |
commit | commitdiff | tree |
| 2026-07-14 |
Pascal | ui: fix mcp panel for toggle + timeout + proxy + ON... |
commit | commitdiff | tree |
| 2026-07-14 |
Aman Gupta | DeepseekV4: fix seq_rm (#25588) |
commit | commitdiff | tree |
| 2026-07-14 |
Jeff Bolz | vulkan/cpu: Support f16 as SET_ROWS src. (#25432) |
commit | commitdiff | tree |
| 2026-07-14 |
Adrien Gallouët | tokenize : align usage by using common args (#25516) |
commit | commitdiff | tree |
| 2026-07-14 |
fairydreaming | ggml : add a set of functions for checking contiguity... |
commit | commitdiff | tree |
| 2026-07-14 |
Christian Kastner | tests: export-graph-ops: exit gracefully when called... |
commit | commitdiff | tree |
| 2026-07-14 |
JusteLeo | ggml: uniformize im2col dst_type for all conv ops ... |
commit | commitdiff | tree |
| 2026-07-14 |
Charles Xu | kleidiai : add SME2 f32 kernel (#24414) |
commit | commitdiff | tree |
| 2026-07-14 |
Pascal | ui: add reasoning effort control to mobile add sheet... |
commit | commitdiff | tree |
| 2026-07-14 |
Thiago Padilha | convert_hf_to_gguf: support split MTP export for HY... |
commit | commitdiff | tree |
| 2026-07-14 |
Christian Kastner | arg: Flush log before exiting after usage() (#25504) |
commit | commitdiff | tree |
| 2026-07-14 |
Titaniumtown | sycl: set fattn_vec_nthreads to 256 for Battlemage... |
commit | commitdiff | tree |
| 2026-07-14 |
Pasha Khosravi | metal : add Q2_0 support (#25419) |
commit | commitdiff | tree |
| 2026-07-13 |
Satinder Grewal | model: add Hy3 (hy_v3) support with MTP speculative... |
commit | commitdiff | tree |
| 2026-07-13 |
Johannes Gäßler | CUDA: refactor MMQ kernel configuration (#24127) |
commit | commitdiff | tree |
| 2026-07-13 |
Jeff Bolz | vulkan: Use native e2m1 and e4m3 conversions for mxfp4... |
commit | commitdiff | tree |
| 2026-07-13 |
Adrian | spec: add Minimax2 eagle3 support |
commit | commitdiff | tree |
| 2026-07-13 |
Georgi Gerganov | readme : add link to maintainer PRs (#25621) |
commit | commitdiff | tree |
| 2026-07-13 |
Christian Kastner | tests: Harmonize header use (#25616) |
commit | commitdiff | tree |
| 2026-07-13 |
QuintinShaw | gguf : add tensor shape accessor (#24405) |
commit | commitdiff | tree |
| 2026-07-13 |
Frosty40 | chat : fix reasoning leak with force-opened bare <think... |
commit | commitdiff | tree |
| 2026-07-13 |
Frosty40 | sycl: add fused top-k MoE (#25217) |
commit | commitdiff | tree |
| 2026-07-13 |
Todd Malsbary | sycl: add Q2_K to DMMV reorder path (#25064) |
commit | commitdiff | tree |
| 2026-07-13 |
Aleksander... | ui: Remove recommended MCP Servers + improve MCP Server... |
commit | commitdiff | tree |
| 2026-07-12 |
Bernard Ladenthin | server: honour per-request reasoning_budget_tokens... |
commit | commitdiff | tree |
| 2026-07-12 |
Alessandro... | vendor : update cpp-httplib to 0.50.1 (#25576) |
commit | commitdiff | tree |
| 2026-07-12 |
Sebastian Dröge | server: Don't consider models with --no-mmproj-auto... |
commit | commitdiff | tree |
| 2026-07-12 |
Pascal | mtmd: fix silent prompt truncation on embedded NUL... |
commit | commitdiff | tree |
| 2026-07-12 |
Aldehir Rojas | server : evict checkpoints within min-step of each... |
commit | commitdiff | tree |
| 2026-07-12 |
quei | server : fix image blocks in tool_result being dropped... |
commit | commitdiff | tree |
| 2026-07-11 |
kdkd | Fix conditional to display 'LLAMA_SPLIT_MODE_TENSOR... |
commit | commitdiff | tree |
| 2026-07-11 |
Rohit Mahesh | gguf : reject empty metadata keys (#24917) |
commit | commitdiff | tree |
| 2026-07-11 |
cphlipot | cuda: Don't crash when querying memory on device with... |
commit | commitdiff | tree |
| 2026-07-11 |
Aman Gupta | DeepseekV4: clear cache only for seq rather than full... |
commit | commitdiff | tree |
| 2026-07-11 |
Xuan-Son Nguyen | server: allow stream for exec_shell_command (#25526) |
commit | commitdiff | tree |
| 2026-07-11 |
Xuan-Son Nguyen | server: refactor server_stream (#25541) |
commit | commitdiff | tree |
| 2026-07-11 |
fairydreaming | ggml : add GGML_OP_LIGHTNING_INDEXER that implements... |
commit | commitdiff | tree |
| 2026-07-11 |
Raman Shinde | Vulkan: route large matmuls to medium tile on Adreno... |
commit | commitdiff | tree |
| 2026-07-11 |
Hongqiang Wang | opencl: add int8 dp4 dense and MoE prefill optimization... |
commit | commitdiff | tree |
| 2026-07-10 |
Pascal | server: accept null sampling params (#25538) |
commit | commitdiff | tree |
| 2026-07-10 |
eduardopessin | llama : make tensor-split regex patterns static (#24710) |
commit | commitdiff | tree |
| 2026-07-10 |
Max Krasnyansky | hexagon: improve ARGSORT performance for small tensors... |
commit | commitdiff | tree |
| 2026-07-10 |
Xuan-Son Nguyen | arg: prevent duplicate spec model downloads (#25527) |
commit | commitdiff | tree |
| 2026-07-10 |
Xuan-Son Nguyen | mtmd: deepseek-ocr v1 multi-tile (#24717) |
commit | commitdiff | tree |
| 2026-07-10 |
felix | feat: pre-select models in the webui using alias (... |
commit | commitdiff | tree |
| 2026-07-10 |
Josh Leverette | ui: use server modalities in non-router mode (#24874) |
commit | commitdiff | tree |
| 2026-07-10 |
Xuan-Son Nguyen | server: remove loading.html (#25500) |
commit | commitdiff | tree |
| 2026-07-10 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-07-10 |
Georgi Gerganov | ggml : use ggml_vqtbl1q_u8 for 32-bit compat (whisper/0) |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / llama.cpp / shortlog