| 2026-05-08 |
Pascal | cuda: fuse snake activation (mul, sin, sqr, mul, add... |
commit | commitdiff | tree |
| 2026-05-08 |
Aleksander... | webui: Add Import/Export of Settings configuration... |
commit | commitdiff | tree |
| 2026-05-08 |
Johannes Gäßler | CUDA: lower-case PCI bus id, standardize for ggml ... |
commit | commitdiff | tree |
| 2026-05-08 |
miyan | vulkan: fix spv shadowing (#22760) |
commit | commitdiff | tree |
| 2026-05-08 |
Max Krasnyansky | ggml: update SCHED_DEBUG output to use ggml_op_desc... |
commit | commitdiff | tree |
| 2026-05-08 |
Shawn Gu | opencl: add q4_0 MoE GEMM for Adreno (#22731) |
commit | commitdiff | tree |
| 2026-05-08 |
Michał Piszczek | convert : fix RuntimeError when stripping FP8 KV-cache... |
commit | commitdiff | tree |
| 2026-05-08 |
Neo Zhang | fix script error (#22795sycl : ) |
commit | commitdiff | tree |
| 2026-05-07 |
samuraieng | model: Support sarashina2.2-vision-3b model (#22103) |
commit | commitdiff | tree |
| 2026-05-07 |
leonardHONG | CUDA: batch out_prod inner loop with cublasSgemmStrided... |
commit | commitdiff | tree |
| 2026-05-07 |
smugman-dot | webui: add option for LLM title generation (#22265) |
commit | commitdiff | tree |
| 2026-05-07 |
Georgi Gerganov | llama : fix device state save/load (#22805) |
commit | commitdiff | tree |
| 2026-05-07 |
shaofeiqi | opencl: add opfilter regex for debugging (#22782) |
commit | commitdiff | tree |
| 2026-05-07 |
Aldehir Rojas | common/chat : preserve media markers for typed-content... |
commit | commitdiff | tree |
| 2026-05-07 |
HaoJun ZHANG | tests: add long-sequence cases and fix inputs for gated... |
commit | commitdiff | tree |
| 2026-05-07 |
Intel AI Get... | sycl: add FILL, CUMSUM, DIAG, SOLVE_TRI, SSM_SCAN,... |
commit | commitdiff | tree |
| 2026-05-07 |
Gaurav Garg | Write a readme on Multi-GPU usage in llama.cpp (#22729) |
commit | commitdiff | tree |
| 2026-05-07 |
Georgi Gerganov | llama : remove unnecessary seq_id check during state... |
commit | commitdiff | tree |
| 2026-05-07 |
pl752 | ggml-cpu: Optimized risc-v cpu q1_0 dot |
commit | commitdiff | tree |
| 2026-05-07 |
Pascal | mtmd: fix whisper audio tail truncation by exposing... |
commit | commitdiff | tree |
| 2026-05-07 |
AesSedai | model: Add Mimo v2.5 model support (#22493) |
commit | commitdiff | tree |
| 2026-05-07 |
Pascal | webui: fix ?model= URL param race in router mode (... |
commit | commitdiff | tree |
| 2026-05-07 |
Vishal Singh | codeowners : add ZenDNN backend codeowner (#22772) |
commit | commitdiff | tree |
| 2026-05-07 |
viggy | webui: fix flicker issue on dismiss animation on overla... |
commit | commitdiff | tree |
| 2026-05-07 |
Shane Tran... | sycl : fix test script (#22737) |
commit | commitdiff | tree |
| 2026-05-07 |
Adrien Gallouët | llama : add missing call to ggml_backend_load_all(... |
commit | commitdiff | tree |
| 2026-05-06 |
tc-mb | mtmd : support MiniCPM-V 4.6 (#22529) |
commit | commitdiff | tree |
| 2026-05-06 |
Gilad S. | model : don't crash on unsupported architecture (#22742) |
commit | commitdiff | tree |
| 2026-05-06 |
fl0rianr | common: do not fit to unknown device memory (#22614) |
commit | commitdiff | tree |
| 2026-05-06 |
Georgi Gerganov | gguf-py : bump version to 0.19.0 (#22664) |
commit | commitdiff | tree |
| 2026-05-06 |
Yakine Tahtah | mtmd: add granite-speech support (ibm-granite/granite... |
commit | commitdiff | tree |
| 2026-05-06 |
David Huggins... | feat: migrate to PEP 621 and add uv support (#21907) |
commit | commitdiff | tree |
| 2026-05-06 |
Daniel Bevenius | convert : ignore non-language tensors for Gemma4Model... |
commit | commitdiff | tree |
| 2026-05-06 |
Aleksander... | webui: Remove Google Favicons & Improve MCP Information... |
commit | commitdiff | tree |
| 2026-05-06 |
zzzzwc | ggml-cpu: fuse RMS_NORM + MUL on CPU backend (#22423) |
commit | commitdiff | tree |
| 2026-05-06 |
viggy | add tabindex and aria-hidden (#22699) |
commit | commitdiff | tree |
| 2026-05-06 |
Sigbjørn Skjæret | convert : add filter_tensors method to pre-filter tenso... |
commit | commitdiff | tree |
| 2026-05-06 |
fl0rianr | ggml : use `CL_DEVICE_GLOBAL_MEM_SIZE` as memory estima... |
commit | commitdiff | tree |
| 2026-05-05 |
Trivikram Reddy | Hexagon: Process M-tail rows on HMX instead of HVX... |
commit | commitdiff | tree |
| 2026-05-05 |
lhez | opencl: refactor Adreno q4_0 (#22335) |
commit | commitdiff | tree |
| 2026-05-05 |
Radoslav Gerganov | rpc : use graph uid instead of graph cache (#22701) |
commit | commitdiff | tree |
| 2026-05-05 |
Adrien Gallouët | common : fix missing-noreturn warnings when compiling... |
commit | commitdiff | tree |
| 2026-05-05 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-05-05 |
Georgi Gerganov | ggml : bump version to 0.11.0 (ggml/1478) |
commit | commitdiff | tree |
| 2026-05-05 |
Adrien Gallouët | common : only load backends when required (#22290) |
commit | commitdiff | tree |
| 2026-05-05 |
Alessandro... | vendor : update cpp-httplib to 0.43.3 (#22686) |
commit | commitdiff | tree |
| 2026-05-05 |
Georgi Gerganov | server : validate --tools CLI argument against known... |
commit | commitdiff | tree |
| 2026-05-05 |
Georgi Gerganov | llama : add option to save memory in device buffers... |
commit | commitdiff | tree |
| 2026-05-05 |
Sigbjørn Skjæret | graph : handle non-contiguous Q/K/V in mul_mat_aux... |
commit | commitdiff | tree |
| 2026-05-05 |
Ismail | ggml : implement fast walsh-hadamard transform for... |
commit | commitdiff | tree |
| 2026-05-04 |
Charles Xu | kleidiai : update to v1.24.0 and use release archive... |
commit | commitdiff | tree |
| 2026-05-04 |
leonardHONG | CUDA: use fastdiv for batch index split in get_rows... |
commit | commitdiff | tree |
| 2026-05-04 |
Xuan-Son Nguyen | server: implement /models?reload=1 (#21848) |
commit | commitdiff | tree |
| 2026-05-04 |
Shakhnazar... | examples: refactor diffusion generation (#22590) |
commit | commitdiff | tree |
| 2026-05-04 |
JusteLeo | webui : fix circular dependency between chat.service... |
commit | commitdiff | tree |
| 2026-05-04 |
Piotr Wilkin... | common/autoparser: fixes for newline handling / forced... |
commit | commitdiff | tree |
| 2026-05-04 |
Xuan-Son Nguyen | model: move `load_hparams` and `load_tensors` to per... |
commit | commitdiff | tree |
| 2026-05-04 |
Evan Huus | server: Add a simple get_datetime server tool (#22649) |
commit | commitdiff | tree |
| 2026-05-04 |
Nick Towle | webui: restore missing settings (#22666) |
commit | commitdiff | tree |
| 2026-05-04 |
Georgi Gerganov | docs : update speculative decoding parameters after... |
commit | commitdiff | tree |
| 2026-05-04 |
Atomic-Germ | vulkan: delete dead GGML_VK_MAX_NODES def (#22621) |
commit | commitdiff | tree |
| 2026-05-04 |
Chen Yuan | ggml-webgpu: add layer norm ops (#22406) |
commit | commitdiff | tree |
| 2026-05-03 |
Aldehir Rojas | common : determine generation prompt using longest... |
commit | commitdiff | tree |
| 2026-05-03 |
Julien Denize | convert : Mistral format yarn apply_scale support... |
commit | commitdiff | tree |
| 2026-05-03 |
JM Robles | convert : apply Q/K RoPE permutation in NVFP4 repack... |
commit | commitdiff | tree |
| 2026-05-02 |
lucy | fix: CUDA device PCI bus ID de-dupe OOMing (ignoring... |
commit | commitdiff | tree |
| 2026-05-02 |
Georgi Gerganov | server : avoid checkpoint data host copies (#22558) |
commit | commitdiff | tree |
| 2026-05-02 |
JusteLeo | ggml-virtgpu: fix circular dependency in headers (... |
commit | commitdiff | tree |
| 2026-05-02 |
Csaba Kecskemeti | convert : disable uint types (#18908) |
commit | commitdiff | tree |
| 2026-05-02 |
Shawn Gu | opencl: Adreno optimization for MoE - MxFP4 (#22301) |
commit | commitdiff | tree |
| 2026-05-02 |
Johannes Gäßler | Github: update issue templates (#22594) |
commit | commitdiff | tree |
| 2026-05-02 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-05-02 |
Georgi Gerganov | ggml : bump version to 0.10.2 (ggml/1474) |
commit | commitdiff | tree |
| 2026-05-02 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-05-02 |
Georgi Gerganov | ggml : try fix win32 build (whisper/0) |
commit | commitdiff | tree |
| 2026-05-02 |
Yiwei Shao | hexagon: hmx flash attention (#22347) |
commit | commitdiff | tree |
| 2026-05-01 |
ddh0 | llama-quant : fix `--tensor-type` when default `qtype... |
commit | commitdiff | tree |
| 2026-05-01 |
Aparna M P | hexagon: enable non-contiguous row tensor support for... |
commit | commitdiff | tree |
| 2026-05-01 |
Aleksander... | webui: Spring Cleaning Refactor v1 (#22505) |
commit | commitdiff | tree |
| 2026-05-01 |
Masashi Yoshimura | ggml-webgpu: Fix vectorized handling in mul-mat and... |
commit | commitdiff | tree |
| 2026-05-01 |
Jeff Bolz | vulkan: Support asymmetric FA in coopmat2 path (#21753) |
commit | commitdiff | tree |
| 2026-05-01 |
Chen Yuan | ggml-webgpu: add the upscale shader (#22419) |
commit | commitdiff | tree |
| 2026-04-30 |
Masashi Yoshimura | ggml-webgpu: Improve performance of mat-vec and mat... |
commit | commitdiff | tree |
| 2026-04-30 |
Reese Levine | Update llama-mmap to use ftello/fseeko (#22497) |
commit | commitdiff | tree |
| 2026-04-30 |
Adrien Gallouët | common : check for null getpwuid in hf-cache (#22550) |
commit | commitdiff | tree |
| 2026-04-30 |
Ruben Ortlam | vulkan: add get/set tensor 2d functions (#22514) |
commit | commitdiff | tree |
| 2026-04-30 |
Ben Guidarelli | spec: fix argument typo (#22552) |
commit | commitdiff | tree |
| 2026-04-30 |
Sigbjørn Skjæret | ci : bump ty to 0.0.33 (#22535) |
commit | commitdiff | tree |
| 2026-04-30 |
Adrien Gallouët | vendor : update cpp-httplib to 0.43.2 (#22548) |
commit | commitdiff | tree |
| 2026-04-30 |
Johannes Gäßler | CUDA: fix tile FA kernel on Pascal (#22541) |
commit | commitdiff | tree |
| 2026-04-30 |
Georgi Gerganov | scripts : add wc2wt.sh - create worktree from current... |
commit | commitdiff | tree |
| 2026-04-30 |
Rithik Sharma | add fast matmul iquants (#22504) |
commit | commitdiff | tree |
| 2026-04-30 |
Georgi Gerganov | spec : fix draft model checkpoints (#22521) |
commit | commitdiff | tree |
| 2026-04-30 |
Peter Sideris | spec : fix vocab compat checks in spec example (#22426) |
commit | commitdiff | tree |
| 2026-04-29 |
Aldehir Rojas | common : do not pass prompt tokens to reasoning budget... |
commit | commitdiff | tree |
| 2026-04-29 |
Max Krasnyansky | hexagon: make vmem and buffer-size configurable (#22487) |
commit | commitdiff | tree |
| 2026-04-29 |
Anav Prasad | CUDA: fuse SSM_CONV + ADD(bias) + SILU (#22478) |
commit | commitdiff | tree |
| 2026-04-29 |
Georgi Gerganov | spec : disacard last drafted token with low prob (... |
commit | commitdiff | tree |
| 2026-04-29 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2026-04-29 |
Georgi Gerganov | ggml : bump version to 0.10.1 (ggml/1469) |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / llama.cpp / shortlog