| 2026-05-13 |
Pascal | server, webui: support continue generation on reasoning... |
| commitdiff |
| 2026-05-13 |
Xuan-Son Nguyen | ci: validate model naming convention (#22680) |
| commitdiff |
| 2026-05-13 |
Georgi Gerganov | spec : update CLI arguments for better consistency... |
| commitdiff |
| 2026-05-13 |
Sigbjørn Skjæret | llama-eval : enable type check (#22988) |
| commitdiff |
| 2026-05-13 |
Sachin Sharma | ggml-zendnn : adaptive fallback to CPU backend for... |
| commitdiff |
| 2026-05-13 |
Trivikram Reddy | hexagon: eliminate scalar VTCM loads via HVX splat... |
| commitdiff |
| 2026-05-12 |
yzyyzyhhh | opencl: add opt-in Adreno xmem F16xF32 GEMM for prefill... |
| commitdiff |
| 2026-05-12 |
fredzillman | convert : fix Pixtral 12B --mistral-format conversion... |
| commitdiff |
| 2026-05-12 |
Aleksander Grygier | webui: Fix Chat Screen Form box disappearing + autoscro... |
| commitdiff |
| 2026-05-12 |
Xuan-Son Nguyen | mtmd, server, common: expose modalities to /v1/models... |
| commitdiff |
| 2026-05-12 |
Masashi Yoshimura | ggml-webgpu: Enables running gpt-oss-20b (#22906) |
| commitdiff |
| 2026-05-12 |
Chen Yuan | ggml-webgpu: address precision issues for multimodal... |
| commitdiff |
| 2026-05-12 |
Daniel Bevenius | model-conversion : add causal-convert-mmproj target... |
| commitdiff |
| 2026-05-12 |
Georgi Gerganov | examples : add llama-eval (#21152) |
| commitdiff |
| 2026-05-12 |
Masato Nakasaka | vulkan: Fix Windows performance regression on Intel... |
| commitdiff |
| 2026-05-12 |
Jeff Bolz | vulkan: Check shared memory size for mmq shaders (... |
| commitdiff |
| 2026-05-12 |
Sigbjørn Skjæret | ci : bump ty to 0.0.35 (#22961) |
| commitdiff |
| 2026-05-12 |
AesSedai | mtmd: add MiMo v2.5 vision (#22883) |
| commitdiff |
| 2026-05-12 |
Jesus Talavera | convert : add split() to LoraTorchTensor in LoRA conver... |
| commitdiff |
| 2026-05-12 |
guyfischman | metal : promote mul_mv/mul_mm batch divisors to functio... |
| commitdiff |
| 2026-05-11 |
Shawn Gu | opencl: add q4_1 MoE for Adreno (#22856) |
| commitdiff |
| 2026-05-11 |
CrispStrobe | CUDA: handle OW > 65535 in im2col (2D and 3D) (#22944) |
| commitdiff |
| 2026-05-11 |
Pascal | Ggml/cuda snake fusion hardening (#22912) |
| commitdiff |
| 2026-05-11 |
willjoha | docs: fix metrics endpoint description in server README... |
| commitdiff |
| 2026-05-11 |
Georgi Gerganov | spec : parallel drafting support (#22838) |
| commitdiff |
| 2026-05-11 |
Kevin Pouget | ggml-virtgpu: Add a GHA build check (#22943) |
| commitdiff |
| 2026-05-11 |
Daniel Bevenius | examples : update args speculative-simple README.md... |
| commitdiff |
| 2026-05-11 |
Jeff Bolz | vulkan: Support asymmetric FA in scalar/mmq/coopmat1... |
| commitdiff |
| 2026-05-11 |
Oliver Simons | CUDA: directly include cuda/iterator (#22936) |
| commitdiff |
| 2026-05-11 |
Daniel Bevenius | convert : add image break token fallback (#22914) |
| commitdiff |
| 2026-05-11 |
Alessandro de Oliv... | vendor : update cpp-httplib to 0.44.0 (#22919) |
| commitdiff |
| 2026-05-11 |
Neo Zhang | [SYCL] Add OP im2col_3d (#22903) |
| commitdiff |
| 2026-05-10 |
Georgi Gerganov | server : print warning when HTTP timeout exceeded ... |
| commitdiff |
| 2026-05-10 |
Tim Neumann | backend sampling: support returning post-sampling probs... |
| commitdiff |
| 2026-05-10 |
Alessandro de Oliv... | vendor : update cpp-httplib to 0.43.4 (#22888) |
| commitdiff |
| 2026-05-10 |
Oliver Walsh | ggml-virtgpu : include missing mutex header (#22810) |
| commitdiff |
| 2026-05-10 |
Georgi Gerganov | sync : ggml |
| commitdiff |
| 2026-05-10 |
Georgi Gerganov | ggml : bump version to 0.11.1 (ggml/1484) |
| commitdiff |
| 2026-05-10 |
scutler-nv | internal AllReduce kernel for CUDA provider (#22299) |
| commitdiff |
| 2026-05-10 |
Sigbjørn Skjæret | model : fix model type check for granite/llama3 and... |
| commitdiff |
| 2026-05-09 |
Sumit Chatterjee | model : add sarvam_moe architecture support (#20275) |
| commitdiff |
| 2026-05-09 |
Yuannan | devops : updated Nix systems (#22869) |
| commitdiff |
| 2026-05-09 |
Davi Henrique Linhares | docker : upgraded the default intel compute-runtime... |
| commitdiff |
| 2026-05-09 |
Alessandro de Oliv... | cmake : update BoringSSL to 0.20260508.0 (#22839) |
| commitdiff |
| 2026-05-09 |
Alexey Kopytko | SYCL: reduce allocation overhead during flash attention... |
| commitdiff |
| 2026-05-09 |
Devedse | [SYCL] Add BF16 support to GET_ROWS operation (#21391) |
| commitdiff |
| 2026-05-09 |
Intel AI Get-to... | sycl: Q5_K reorder MMVQ/dequant + Q8_0 reorder MMVQ... |
| commitdiff |
| 2026-05-09 |
Intel AI Get-to... | sycl: Battlemage AOT build via spir64_gen + MMQ subgrou... |
| commitdiff |
| 2026-05-09 |
AesSedai | Add flash attention MMA / Tiles to support MiMo-V2... |
| commitdiff |
| 2026-05-09 |
Yanzhao Wang | hexagon: add HTP kernel for GGML_OP_GATED_DELTA_NET... |
| commitdiff |
| 2026-05-09 |
Intel AI Get-to... | sycl: support non-contiguous input in PAD op (#22148) |
| commitdiff |
| 2026-05-08 |
Pranav Dhinakar | Feature hexagon l2 norm (#22816) |
| commitdiff |
| 2026-05-08 |
Aldehir Rojas | common : do not wrap raw strings in schema parser for... |
| commitdiff |
| 2026-05-08 |
ynankani | model : support Gemma4_26B_A4B_NVFP4 (#22804) |
| commitdiff |
| 2026-05-08 |
Aldehir Rojas | common : revert reasoning budget +inf logit bias (... |
| commitdiff |
| 2026-05-08 |
smugman-dot | webui: fix LLM title generation for agentic conversatio... |
| commitdiff |
| 2026-05-08 |
Xuan-Son Nguyen | server: support Vertex AI compatible API (#22545) |
| commitdiff |
| 2026-05-08 |
Xuan-Son Nguyen | server: (router) expose child model info from router... |
| commitdiff |
| 2026-05-08 |
Pascal | cuda: fuse snake activation (mul, sin, sqr, mul, add... |
| commitdiff |
| 2026-05-08 |
Aleksander Grygier | webui: Add Import/Export of Settings configuration... |
| commitdiff |
| 2026-05-08 |
Johannes Gäßler | CUDA: lower-case PCI bus id, standardize for ggml ... |
| commitdiff |
| 2026-05-08 |
miyan | vulkan: fix spv shadowing (#22760) |
| commitdiff |
| 2026-05-08 |
Max Krasnyansky | ggml: update SCHED_DEBUG output to use ggml_op_desc... |
| commitdiff |
| 2026-05-08 |
Shawn Gu | opencl: add q4_0 MoE GEMM for Adreno (#22731) |
| commitdiff |
| 2026-05-08 |
Michał Piszczek | convert : fix RuntimeError when stripping FP8 KV-cache... |
| commitdiff |
| 2026-05-08 |
Neo Zhang | fix script error (#22795sycl : ) |
| commitdiff |
| 2026-05-07 |
samuraieng | model: Support sarashina2.2-vision-3b model (#22103) |
| commitdiff |
| 2026-05-07 |
leonardHONG | CUDA: batch out_prod inner loop with cublasSgemmStrided... |
| commitdiff |
| 2026-05-07 |
smugman-dot | webui: add option for LLM title generation (#22265) |
| commitdiff |
| 2026-05-07 |
Georgi Gerganov | llama : fix device state save/load (#22805) |
| commitdiff |
| 2026-05-07 |
shaofeiqi | opencl: add opfilter regex for debugging (#22782) |
| commitdiff |
| 2026-05-07 |
Aldehir Rojas | common/chat : preserve media markers for typed-content... |
| commitdiff |
| 2026-05-07 |
HaoJun ZHANG | tests: add long-sequence cases and fix inputs for gated... |
| commitdiff |
| 2026-05-07 |
Intel AI Get-to... | sycl: add FILL, CUMSUM, DIAG, SOLVE_TRI, SSM_SCAN,... |
| commitdiff |
| 2026-05-07 |
Gaurav Garg | Write a readme on Multi-GPU usage in llama.cpp (#22729) |
| commitdiff |
| 2026-05-07 |
Georgi Gerganov | llama : remove unnecessary seq_id check during state... |
| commitdiff |
| 2026-05-07 |
pl752 | ggml-cpu: Optimized risc-v cpu q1_0 dot |
| commitdiff |
| 2026-05-07 |
Pascal | mtmd: fix whisper audio tail truncation by exposing... |
| commitdiff |
| 2026-05-07 |
AesSedai | model: Add Mimo v2.5 model support (#22493) |
| commitdiff |
| 2026-05-07 |
Pascal | webui: fix ?model= URL param race in router mode (... |
| commitdiff |
| 2026-05-07 |
Vishal Singh | codeowners : add ZenDNN backend codeowner (#22772) |
| commitdiff |
| 2026-05-07 |
viggy | webui: fix flicker issue on dismiss animation on overla... |
| commitdiff |
| 2026-05-07 |
Shane Tran Whitmire | sycl : fix test script (#22737) |
| commitdiff |
| 2026-05-07 |
Adrien Gallouët | llama : add missing call to ggml_backend_load_all(... |
| commitdiff |
| 2026-05-06 |
tc-mb | mtmd : support MiniCPM-V 4.6 (#22529) |
| commitdiff |
| 2026-05-06 |
Gilad S. | model : don't crash on unsupported architecture (#22742) |
| commitdiff |
| 2026-05-06 |
fl0rianr | common: do not fit to unknown device memory (#22614) |
| commitdiff |
| 2026-05-06 |
Georgi Gerganov | gguf-py : bump version to 0.19.0 (#22664) |
| commitdiff |
| 2026-05-06 |
Yakine Tahtah | mtmd: add granite-speech support (ibm-granite/granite... |
| commitdiff |
| 2026-05-06 |
David Huggins-Daines | feat: migrate to PEP 621 and add uv support (#21907) |
| commitdiff |
| 2026-05-06 |
Daniel Bevenius | convert : ignore non-language tensors for Gemma4Model... |
| commitdiff |
| 2026-05-06 |
Aleksander Grygier | webui: Remove Google Favicons & Improve MCP Information... |
| commitdiff |
| 2026-05-06 |
zzzzwc | ggml-cpu: fuse RMS_NORM + MUL on CPU backend (#22423) |
| commitdiff |
| 2026-05-06 |
viggy | add tabindex and aria-hidden (#22699) |
| commitdiff |
| 2026-05-06 |
Sigbjørn Skjæret | convert : add filter_tensors method to pre-filter tenso... |
| commitdiff |
| 2026-05-06 |
fl0rianr | ggml : use `CL_DEVICE_GLOBAL_MEM_SIZE` as memory estima... |
| commitdiff |
| 2026-05-05 |
Trivikram Reddy | Hexagon: Process M-tail rows on HMX instead of HVX... |
| commitdiff |
| 2026-05-05 |
lhez | opencl: refactor Adreno q4_0 (#22335) |
| commitdiff |
| 2026-05-05 |
Radoslav Gerganov | rpc : use graph uid instead of graph cache (#22701) |
| commitdiff |
| 2026-05-05 |
Adrien Gallouët | common : fix missing-noreturn warnings when compiling... |
| commitdiff |
| next |
overview / pkg / ggml / sources / llama.cpp / history