Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
417 commits
Select commit Hold shift + click to select a range
8144f31
ui: Chat Conversation Tabbed navigation (#27263)
allozaur Aug 23, 2026
d337192
[Tensor parallel] Fix meta tensor split state propagation (#27574)
gaugarg-nv Aug 23, 2026
b0539c4
DeepseekV4: fix rollback with multi-seq (#26756)
am17an Aug 23, 2026
ba8e0ed
common : skip device_info loop if it's not going to be printed (#26692)
wolfpld Aug 23, 2026
e8eed45
server : add LLAMA_SERVER_SLOTS_N_DIFF (#27600)
ggerganov Aug 23, 2026
a278dce
contrib : recommend waiting for CI before merging (#27603)
nikwen Aug 23, 2026
95b8e33
ci : add test-llama-archs tensor split for Metal (#27598)
ggerganov Aug 23, 2026
56db501
mtmd: use pillow-accurate algo, correct resize_algo for all models (#…
ngxson Aug 23, 2026
4a08fa2
test: move tools/parser to tests (#27548)
ngxson Aug 23, 2026
8d9af25
test : fix multi-GPU server tests (#27614)
ggerganov Aug 23, 2026
d05f895
fix: Change chat tabs nav shortcuts (#27609)
allozaur Aug 23, 2026
ccc8fd2
readme : update links (#27617)
ggerganov Aug 23, 2026
c060ca9
model : support MTP in GLM-4.5-Air (#26534)
jacekpoplawski Aug 23, 2026
bf0a29c
Deepseek 4: `-sm tensor` (#26490)
am17an Aug 24, 2026
a130532
mamba2 : Flatten in/out projections to dispatch GEMM instead of GEMV …
pskrunner14 Aug 24, 2026
6036c63
ggml : fix ggml_clamp (#27644)
ggerganov Aug 24, 2026
985b149
ci : apply ccache-clear with older/min/dry-run to all ccache jobs (#2…
ggerganov Aug 24, 2026
160c6b0
mtmd: video: fix moov atom at the end of file (#27596)
ngxson Aug 24, 2026
c1c766d
webgpu : reorder includes since V that appears in common_decls.tmpl m…
fairydreaming Aug 24, 2026
a14dba6
ggml : shorten virtual device naming in CUDA and Metal (#27608)
ggerganov Aug 24, 2026
71cc86f
convert: fix GLM regression in index_tensors (#27655)
jacekpoplawski Aug 24, 2026
7584430
tests : disable DOTS3NOTE arch test for WebGPU (#27654)
fairydreaming Aug 24, 2026
b3c3b96
misc : read repetition_penalty from generation_config.json (#27659)
tdakhran Aug 24, 2026
b615f5b
metal: per-op source split + parallel compile (#26561)
forforever73 Aug 24, 2026
f280b26
metal : per-device tuned (Q, NE) for flash-attn vec (#26570)
forforever73 Aug 24, 2026
5ea87dd
webgpu : fix handling of infinity values during ARGSORT and TOP_K (#2…
fairydreaming Aug 25, 2026
814d84b
sycl : mark tq2_0 as not supported (#27660)
arthw Aug 25, 2026
eb25b72
grammar : parse \- in char classes as literal hyphen (#27591)
NIXKnight Aug 25, 2026
9388236
ggml : bump version to 0.22.0 (ggml/1607)
ggerganov Aug 25, 2026
81191af
sync : ggml
ggerganov Aug 25, 2026
c1d0e7a
llama.cpp : bump version to 0.3.0 (#27696)
ggerganov Aug 25, 2026
3737e41
metal : null-check buffer alloc to fix OOM crash (#25371)
ykhrustalev Aug 25, 2026
f1357e4
ui: ESLint config updates (#27700)
allozaur Aug 25, 2026
790b571
ci : store ccache on HF buckets (test with cuda-ubuntu for now) (#27699)
CISC Aug 25, 2026
0cc5b14
chat : scope qwen3-coder workarounds (#27679)
aldehir Aug 25, 2026
1729ed5
server : reject prefilled assistant messages with tool calls (#27626)
kyo-zzz Aug 25, 2026
0a5ac49
devops: use GGML_NATIVE=OFF for OpenVINO (#27338)
krzsztf Aug 25, 2026
b114b47
rpc: support apple RDMA as an RPC transport (#26421)
ryan5rdx Aug 25, 2026
eab8ee4
ci : update OS used for ROCM to Ubuntu 24.04 (#27681)
superm1 Aug 25, 2026
d222767
kleidiai: Rework KleidiAI Build System/Integration (#26077)
JonathanC-ARM Aug 25, 2026
5d5cb4c
ggml-meta: propagate buffer usage and call init on the new tensors (#…
max-krasnyansky Aug 26, 2026
11cd988
ggml-metal: add chunked SSD MMA for Mamba-2 prefill optimization (#26…
dpantaleoni Aug 26, 2026
dac869b
conversion : fix Nemotron 3.5 Lightning layers (#27729)
danbev Aug 26, 2026
da9b5d6
ci : make cache bucket public (#27728)
CISC Aug 26, 2026
fc35562
cuda: unblock mmq for MoE on sm_60 (#26264)
dfriehs Aug 26, 2026
4d19b28
ci: Clean up UI builds from releases (#27706)
allozaur Aug 26, 2026
d0132a6
rpc : implement event and async backend APIs (#18626)
rgerganov Aug 26, 2026
bf94216
Implemented vulkan cross_entropy_loss and cross_entropy_loss_back (#2…
PranavUttarkar Aug 26, 2026
5e6a37c
vulkan: warptiles currently assume warp sizes <= 64, clamp to work ar…
0cc4m Aug 26, 2026
0379a19
ui: Update Dialog component styling (#27743)
allozaur Aug 26, 2026
539f245
ui: Move Settings and MCP Servers routes to dialog-based views (#27744)
allozaur Aug 26, 2026
925e117
llama: add token ID tracking to KV cell (#27762)
ngxson Aug 26, 2026
192067b
hexagon: support for multi-NPU devices (IQ9, IQ10) and fully asynchro…
max-krasnyansky Aug 27, 2026
d7a2074
models : support nanbeige4.2-3B (#27730)
zqlcode Aug 27, 2026
c5fc7e3
llama : add --n-cpu-ffn option (#26622)
John-194 Aug 27, 2026
915dc6d
metal : fix memory leaks due to missing autoreleasepools (#27758)
nikwen Aug 27, 2026
f295512
args: add --video-* CLI arguments (#24318)
ngxson Aug 27, 2026
deae5ee
model : simplify MiniMax-01 graph (#27790)
fairydreaming Aug 27, 2026
2bb9bdd
spec: Add benchmark-only synthetic speculative acceptance options (#2…
gaugarg-nv Aug 27, 2026
fe235f4
ui: Replace per-conversation MCP overrides with per-conversation tool…
allozaur Aug 27, 2026
bcb6084
convert : fix Nemotron-H LoRA GGUF conversion (#27356)
frozenblade1224 Aug 27, 2026
cae6357
ui: Improve Chat Form Actions UI/UX (models selector, add panel) (#27…
allozaur Aug 27, 2026
fac889f
llama: model_loader: add TENSOR_READ_LAZY (#27794)
ngxson Aug 27, 2026
1a946ec
pr2wt : use ssh/https remote in worktree depending on base (#27800)
CISC Aug 27, 2026
cb30059
Feature: Added LIGHTNING_INDEXER support for Deepseek V4 ops on Vulka…
shenron0101 Aug 27, 2026
732707d
quantize: cap working memory size to avoid loading big tensors onto R…
ngxson Aug 27, 2026
5854625
opencl: add bin kernels `kernel_gemm_moe_q4_0_q8_1_dp4a_bin`, `kernel…
shawngu-quic Aug 27, 2026
b10f9ca
spec : add DFlash2 support (local convolution + candidate selector) (…
ngxson Aug 27, 2026
6fdd0ac
ci : bundle HIP runtime DLLs with Windows ROCm release (#26973)
slojosic-amd Aug 27, 2026
6c84c7d
model: add Qwen3.8-Flash-Next (qwen4exp) (#27742)
danielhanchen Aug 27, 2026
3217633
ci : build only the ggml-hip backend for windows-rocm release (#27753)
harkgill-amd Aug 27, 2026
1844325
server: add ctx-per-slot (--kv-unified-per-slot) (#24124)
bartowski1182 Aug 27, 2026
83d855c
hex-unary: fix RMS_NORM_MUL weight-offset bugs for grouped/broadcast …
aparmp-quic Aug 27, 2026
e70802a
ggml-hexagon: add HTP unary ops for ABS and LOG (#27786)
cqderek Aug 27, 2026
ca3d5a3
model: add DSpark support for Nemotron3.5 (#27804)
ruixiang63 Aug 27, 2026
4e97ac8
tests : run test-save-load-state across all architectures (#27755)
ggerganov Aug 28, 2026
6d6b697
metal : add fa-vec tunings for M4 Pro (#27824)
infinitewarp Aug 28, 2026
8963a9b
metal : add fa-vec tunings for M3 Max, M5 and M5 Pro (#27863)
ggerganov Aug 28, 2026
be87620
sycl: bind the f16 KV cache in place for the oneDNN SDPA path (#27468)
Titaniumtown Aug 28, 2026
d077b4c
sycl: use TILE for quantized KV decode on BMG (#26689)
johnkarlhill Aug 28, 2026
b19cbe9
convert: prevent ndarray conversion in LazyChunkedTensor (#27869)
ngxson Aug 28, 2026
511f9c1
OpenVINO: Update OV to 2026.3.1, whisper.cpp support, Qwen3.5 on NPU,…
wine99 Aug 28, 2026
f5e85d4
metal : add fa-vec tunings for M4 (#27875)
Strongtut Aug 28, 2026
8663224
context : disable non-fused GDN and LID ops (#27877)
ggerganov Aug 28, 2026
90c26fc
Vulkan: add hoisting support for row IDs and expert count in shaders …
ravel7524 Aug 28, 2026
a43c398
ggml : fix conv_transpose_2d for multiple batches (#26132)
tekinertekin Aug 28, 2026
b387ddf
vulkan: fix missing view-alias dependencies in ggml_vk_graph_optimize…
Eric-A-Stalee Aug 28, 2026
6fe7498
model: qwen4exp: reduce number of graph splits (#27880)
ngxson Aug 28, 2026
50f068f
bench: add --tensor-read-lazy (#27881)
ngxson Aug 28, 2026
d7bd3bf
snapdragon: python SDK setup (Windows) (#27903)
kurquhar Aug 28, 2026
77f132c
vulkan: Change mul_mat_id to pad K rather than N (#27925)
jeffbolznv Aug 29, 2026
5ea1b12
metal : add fa-vec tunings for M1 Max (#27932)
jhen0409 Aug 29, 2026
c9ca51c
vulkan: combine duplicated fastdiv functions, rename the one optimizi…
jeffbolznv Aug 29, 2026
cc83d7b
sycl: make --fit respect --fit-target better (#27629)
nicois Aug 29, 2026
17252c7
metal : add remaining fa-vec tunings for M4 Pro (#27915)
nikwen Aug 29, 2026
3173a56
metal : assert shared memory padding (#27951)
ggerganov Aug 29, 2026
c841aee
opencl: use a better matmul path on two Adreno GPU generations (#27640)
wanghqc Aug 29, 2026
c589f0e
metal : add fa-vec tunings for M2 (#27940)
ring2003 Aug 29, 2026
57291f2
ggml: allow passing alloc dependencies in graph_optimize (#27301)
am17an Aug 30, 2026
bdf3955
memory : copy Hadamard matrix to k_rot tensor only if it has buffer a…
fairydreaming Aug 30, 2026
d882575
metal : fix null-pipeline crash for F16 src1 mul_mat/mul_mat_id (#25648)
QuintinShaw Aug 30, 2026
370cb12
sycl: split long rows in TOP_K instead of one work-group per row (#27…
Titaniumtown Aug 30, 2026
9e54e68
hexagon: support for device discovery and create sessions on demand (…
max-krasnyansky Aug 30, 2026
2bf0415
rpc : fix pre-rdma macOS versions (#27815)
ryan5rdx Aug 30, 2026
dc7aecf
vendor : update cpp-httplib to 0.54.0 (#27919)
cabelo Aug 30, 2026
b8b743c
metal : Add fa-vec tuning for M3 Pro (#27963)
addianto Aug 30, 2026
093adb2
metal: add fa-vec tunings for M3 Ultra (#27999)
ngladitz Aug 30, 2026
742347b
rpc: fix apple rdma error spew on teardown (#27908)
ryan5rdx Aug 30, 2026
73f56d1
ggml : add ggml_backend_op_alloc_size_may_expand, use it in RPC (#27960)
ggerganov Aug 30, 2026
bebc935
common: rename --tensor-read-lazy to --lazy-mode, add -lzm shorthand …
ggerganov Aug 30, 2026
cc231cb
dflash: pass missing NVFP4 scales to attention operations (#28000)
JamePeng Aug 30, 2026
e422148
hip : optimize Q2_0 dot-product path for gfx1201 (#26753)
LunalFresh Aug 30, 2026
0b5be7e
hip: tune rdna 3 mmq config (#26284)
itterative Aug 30, 2026
f1793c1
CUDA: use the fast mm_ids_helper path for any n_expert_used (#27978)
ServeurpersoCom Aug 30, 2026
2578138
llama: improve TENSOR_READ_LAZY handling (#27837)
ngxson Aug 30, 2026
0190529
ggml: add SWIGLU_CLAMP (#27930)
am17an Aug 30, 2026
62acc89
kv-cells: stop the sequence scan once all sequences are seen (#28011)
ServeurpersoCom Aug 30, 2026
6d1479c
ggml : fix ggml_backend_buft_get_alloc_size() guard (#28038)
ggerganov Aug 30, 2026
a7cc83b
rpc: avoid serializing buffers from other servers (#26500)
hmirin Aug 30, 2026
bd55e6a
metal : add remaining Q4_1/Q5_0/Q5_1 fa-vec tunings for M2 (#28017)
ring2003 Aug 30, 2026
9723942
hexagon: fix CPY fence bug (#28033)
yshsharke Aug 30, 2026
daef7b6
vulkan: top_k radix select for k >= 1024 for Qwen 3.8 Flash Next (#28…
0cc4m Aug 31, 2026
557614e
ggml : add MUL_MAT to the list of ops that may need additional memory…
fairydreaming Aug 31, 2026
2cdae80
vulkan: tune mat-vec rows for batched inference on Strix Halo (#27909)
SimonTeixidor Aug 31, 2026
662a0b0
spec : fuse the DFlash encoder into the KV cache injection (#27310)
wjinxu Aug 31, 2026
580e88d
ci : add check for unzip (#28082)
CISC Aug 31, 2026
a32af33
sycl : Enhance to get the free memory of Intel GPU (#27968)
arthw Aug 31, 2026
41ef91f
CUDA: extend MOE fusion to specdec, earlier MOE glu fusion and topk-r…
ynankani Aug 31, 2026
5d4a3be
metal : add fa-vec tunings for M1 (#28078)
nikwen Aug 31, 2026
f8dbcd6
ROCm: add radix TOP_K for long rows (#27466)
jadenmach2 Aug 31, 2026
8e53fce
webgpu : avoid crash when offset is not multiple of 4 in WebGPU ggml_…
fairydreaming Aug 31, 2026
774ee0e
ui: copy the displayed text of grouped agentic responses (#27832)
ServeurpersoCom Aug 31, 2026
010be96
opencl: tune the quant paths for Intel Xe-LP GPUs to improve its TG a…
wanghqc Aug 31, 2026
2d8d612
kv-cache : optimize restoring non-contiguous cells (#27991)
itsnotoger Aug 31, 2026
2a74817
metal : add top-k radix implementation (#28073)
ggerganov Aug 31, 2026
85c5522
AVX2: Speed up large batch size prompt processing of IQ models (#27402)
bartowski1182 Aug 31, 2026
ab0b3bd
metal : add concat support for quantized types (#28116)
ggerganov Aug 31, 2026
e4b9af0
CUDA: XOR swizzle flash attn K,V smem fp16 tiles (#25635)
ynankani Aug 31, 2026
458681e
metal : add fa-vec tunings for M1 Ultra (#28088)
ozgursoy Aug 31, 2026
09412af
qwen4exp: sum the indexer heads by slices (#28023)
ServeurpersoCom Sep 1, 2026
0eadefe
qwen4exp: support recurrent state rollback (#28123)
ServeurpersoCom Sep 1, 2026
518b762
kleidiai : Update KleidiAI Documentation (#26078)
JonathanC-ARM Sep 1, 2026
234a6eb
ci: Bump ggml-org/ccache-action to v1.2.24 (#28083)
luhenry Sep 1, 2026
d5d993a
metal: enable Metal 4.0 tensor API on M5+/A19+ (#27461)
JamesFranc Sep 1, 2026
1b89a43
quantize: row-slab stream to avoid thread starvation (#27830)
ngxson Sep 1, 2026
d086dbb
tests : fix log verbosity for test-llama-archs (#28147)
ggerganov Sep 1, 2026
36b1015
qwen4exp: fix seq_cp, block position keying, mtmd input, cuda abort, …
danielhanchen Sep 1, 2026
5eec3ad
sycl : support limit max alloc memory within 2GB for host-pinned memo…
arthw Sep 1, 2026
d08c787
metal : add fa-vec tuning for M2 Max (#28015)
ggerganov Sep 1, 2026
fe2120b
metal : fix more leaks due to missing autoreleasepools (#27883)
nikwen Sep 1, 2026
9d81721
model : load hparams.n_layer_nextn before n_layer() calls (#28159)
CISC Sep 1, 2026
be789c3
metal : add fa-vec tunings for A18 Pro (MacBook Neo) (#28152)
jhen0409 Sep 1, 2026
8887a48
metal : add fa-vec tuning for M2 Pro (#28122)
lstolcman Sep 1, 2026
1f3d318
sycl : add Kronecker product FWHT support for sizes 384, 640, 768, 12…
philip-jingxin Sep 1, 2026
c845263
Revert "sycl : add Kronecker product FWHT support for sizes 384, 640,…
Titaniumtown Sep 1, 2026
d11b3cc
model : load relevant arrays with n_layer_all (#28173)
CISC Sep 1, 2026
73159c3
model : fix gemma4-assistant (#28183)
CISC Sep 1, 2026
f28493c
models : appropriately flag noscan ssm_a tensors (#28121)
CISC Sep 1, 2026
dfc29b6
context : autoscale n_ctx_train when yarn scaling specified (#28030)
CISC Sep 1, 2026
b356fa2
kv-cells: look up the n-gram history in the sequence position index (…
ServeurpersoCom Sep 1, 2026
3466812
cuda: fuse MoE weighted expert reduction (#25952)
anujj Sep 1, 2026
b96806d
metal : add metallib build support for xcframework (#28163)
jhen0409 Sep 1, 2026
69320fe
hexagon: add missing FARF logs for cpy/get_rows/set_rows/gdn ops (#28…
trivikram-reddy1 Sep 2, 2026
43d87ff
opencl: fix out‐of‐bound reads in the Adreno image kernels (#27632)
wanghqc Sep 2, 2026
2637dfe
ggml-cpu : conditionally add SpacemiT IME kernel sources (#27961)
alanhc Sep 2, 2026
56dd815
vulkan : only request VK_KHR_shader_bfloat16 extension if supported (…
madsmtm Sep 2, 2026
ba8818c
vulkan: handle larger batch sizes (>4) efficiently for IQ3_S mat-vec …
LaurentZuijdwijk Sep 2, 2026
960dffa
hexagon: MUL_MAT and MUL_MAT_ID fusion and fixes (#28202)
max-krasnyansky Sep 2, 2026
b81c99b
ggml: avoid KleidiAI buffer type init on dispatch (#27891)
ac-mmi Sep 2, 2026
0f3a71b
mtmd: Fix Qwen3-tts-0.6b (#28231)
ServeurpersoCom Sep 2, 2026
8e93a97
CUDA + ggml: add sparse-fa for DSV4/GLM (#27970)
am17an Sep 2, 2026
7798007
mtmd: support DeepSeek-V4-Flash-Vision-Exp (#28133)
ngxson Sep 2, 2026
e750b88
common, server : enable preserve_reasoning kwarg by default, log its …
ggerganov Sep 2, 2026
3d3d7c8
ggml-cuda : remove unused vars (#28235)
angt Sep 2, 2026
d5fec32
ci : enable hf-jobs on server-cuda (#28258)
CISC Sep 2, 2026
9400c89
model: correctly support input vision for deepseek4 (#28154)
ngxson Sep 2, 2026
cff1844
Update ROCm to 10.0.0 release (#27803)
superm1 Sep 2, 2026
03dbcc5
ci : check for missing autoreleasepools (#27884)
nikwen Sep 2, 2026
8c0b9cd
metal : fix memory query under low-memory conditions (#27701)
madsmtm Sep 2, 2026
9cc3394
metal : add fa-vec tunings for M3 (#28236)
init-22 Sep 2, 2026
7339054
mtmd: add mtmd_tokenize_from_parts() (#28250)
ngxson Sep 2, 2026
f027c4f
ggml-hexagon: add F16 support for unary ops (#28228)
cqderek Sep 2, 2026
9cffdcc
server : accept data: URLs for input_video and input_audio (#27735)
geckguy Sep 2, 2026
159b741
finetune: fix no KV cache (#27199)
ngxson Sep 2, 2026
67a17c1
mtmd: fix idefics3 preproc (#28273)
ngxson Sep 2, 2026
c61b98b
model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support…
YanissAmz Sep 3, 2026
4aa6ffb
sycl: reduce redundant work in Q4_K multi-column MMVQ (#27062)
Eurekatic Sep 3, 2026
5ec4eab
misc : prevent RAM peaking at model loading stage (#27483)
tdakhran Sep 3, 2026
d646c9d
convert : skip bias_vl tensor in DeepSeek-V4 DSpark conversion (#28294)
ggerganov Sep 3, 2026
0df974d
sycl : enhance the api to support peer-to-peer copy (#27550)
arthw Sep 3, 2026
c7bda03
vulkan: fix FA dequant path engagement (#28190)
Nathanw1014 Sep 3, 2026
0ba6499
CUDA: Allow concurrent streams per split for multi-GPU (#28198)
tannerbruhn Sep 3, 2026
f45576a
mtmd : add `const` in various places (#28307)
madsmtm Sep 3, 2026
0df017d
metal : fix glu dispatch with ne00 = 1 (#28306)
ggerganov Sep 3, 2026
7bb0fc1
metal : add sparse FA (#28098)
ggerganov Sep 3, 2026
de8656b
mtmd: propagate const to preproc class (#28310)
ngxson Sep 3, 2026
42f0225
server : use pytest-xdist for server tests (#28298)
danbev Sep 3, 2026
e107984
ops: add Hexagon to ops.md and update main README.md (#28263)
tboinovski1 Sep 3, 2026
d30500b
snapdragon: ci updates to use new run script (#28293)
max-krasnyansky Sep 3, 2026
8c1a251
tune MMVQ to MMQ crossover for SM87 (#28285)
kbenkhaled Sep 3, 2026
95ef7fc
opencl: quant lm_head / decode GEMV and medium-batch GEMM optimizatio…
wanghqc Sep 3, 2026
c5a5535
common/json-schema : fix GBNF grammar generation for empty object sch…
SergeySklyarov Sep 3, 2026
d230ddd
llama: fix whole source code rebuilt on each new commit (#28278)
ngxson Sep 3, 2026
f9f09f0
SYCL: Refactor GGML_SYCL_ENABLE_MKL_FA to global var (#26863)
johnkarlhill Sep 4, 2026
6703d78
sycl: fuse rms_norm+mul+add and add+add residual chains (#27610)
newjordan Sep 4, 2026
9a4843c
src : add n_expert_used_max function (#28323)
danbev Sep 4, 2026
832fd6f
ggml-cpu(s390x) : fix q5_1 uninitialized v_acc (#28332)
taronaeo Sep 4, 2026
c390d0a
common : make build info output stream configurable (#28322)
angt Sep 4, 2026
0ef4d56
ci : disable failing openvino tests (#28347)
ravi9 Sep 4, 2026
38521ec
vendor: update BoringSSL to 0.20260903.0 (#28354)
cabelo Sep 4, 2026
a529af9
docs : update maintainer PRs link and regenerate AUTHORS (#28365)
ggerganov Sep 4, 2026
24f5bf8
ggml : remove GGML_CUDA_PEER_MAX_BATCH_SIZE (#28177)
angt Sep 4, 2026
4cbe8b0
ggml : don't crash when backend search path can't be read (#28271)
angt Sep 4, 2026
d509cb1
Don't use npx inside a package.json script (#28270)
eapache Sep 4, 2026
86b351f
ggml : replace compile definitions with version.h.in (#28364)
danbev Sep 4, 2026
8f83678
metal : add remaining fa-vec tunings for M3 Max (#28373)
nikwen Sep 4, 2026
163a407
model, mtmd: fix gemma4 vision handling (#28335)
ngxson Sep 4, 2026
64a155d
sync : ggml (#28379)
ggerganov Sep 4, 2026
5266f24
llama.cpp : bump version to 0.4.0 (#28386)
ggerganov Sep 4, 2026
49c0dc8
model : add Tencent Hy 4 (hy_v4) preview architecture support (#28127)
Little0o0 Sep 4, 2026
1863ac0
ui: export conversations from database instead of cached store (#27432)
intel00000 Sep 4, 2026
8b4b355
ci : move more jobs to ccache-buckets (#28375)
CISC Sep 4, 2026
4acf4a4
opencl: add Adreno xmem SDPA path (#26331)
happyyzy Sep 4, 2026
1548a24
opencl: extend the elementwise and data‐movement op coverage (#27633)
wanghqc Sep 4, 2026
85d5703
ui : fix MCP image attachments not displayed in tool block (#25789) (…
nachobh Sep 4, 2026
427291b
metal : add remaining fa-vec tunings for M3 (#28396)
init-22 Sep 4, 2026
cd8cdf3
sycl: attribute device allocations by site (GGML_SYCL_MEMTRACE) (#27631)
nicois Sep 5, 2026
4d91760
sycl : fix test-backend-ops CI break && restore Kronecker product FWH…
philip-jingxin Sep 5, 2026
6a1a922
metal : fix memory leak in early return (#28399)
nikwen Sep 5, 2026
74a7c89
Github: limit blank issues to maintainers (#28435)
JohannesGaessler Sep 5, 2026
971595d
metal : add remaining fa-vec tunings for M2 Max (#28458)
nikwen Sep 6, 2026
c457e3b
ui : embed assets directly with CMake (#28445)
angt Sep 6, 2026
7620399
common: add --log-jsonl (#28437)
ngxson Sep 6, 2026
0afb805
ui: Improve Chat Messages rendering performance (#28460)
allozaur Sep 6, 2026
9e0e220
grammar : fix max repetition threshold (#28469)
aldehir Sep 6, 2026
73a43d1
cuda: fixes races in mmid and mmf (#28475)
am17an Sep 6, 2026
d03efa5
opencl: properly choose weights pack for q4_K, q5_K mul_mat (#28402)
lhez Sep 6, 2026
3ad1ba7
[Model] Support for Spark2_5ForCausalLM implementation (#27868)
KnightYao Sep 6, 2026
5fdfa62
models : fix GDN normalization from `max` to `rsqrt` (#28068)
danielhanchen Sep 6, 2026
465e49b
convert : add `--fuse-qkv` flag to fuse Q/K/V into QKV during HF-to-G…
JoursBleu Sep 6, 2026
8fe90e1
vulkan: add TQ1_0 support (mm, mat-vec, mat-vec-id, dequant, get_rows…
Anjielon Sep 7, 2026
2092353
ci : add container image checking and tagging (wip) (#28394)
danbev Sep 7, 2026
9ac8c40
vulkan: rms_norm fusion opportunities (#28024)
jeffbolznv Sep 7, 2026
992cb50
ggml: allow backend inputs to not create another split (#28387)
am17an Sep 7, 2026
b74f590
ggml-cuda: fix divergent barrier in f16 flash attention (#27870)
siavashnorouzi Sep 7, 2026
9a75705
convert : write explicit recurrent_layers for Qwen3-Next / Qwen3.5 (#…
devvexus Sep 7, 2026
5202104
caps : recheck typed content if template checks for string (#28511)
CISC Sep 7, 2026
1173700
examples : print ggml_version and ggml_commit in test-cmake [no ci] (…
danbev Sep 7, 2026
0cae430
vulkan: support type-aligned GET_ROWS (#28253)
jeffbolznv Sep 7, 2026
8551006
jimwu.fix-test-recurrent-state-rollback-rocm: 1 file changed, 7 inse…
Sep 19, 2026
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
23 changes: 13 additions & 10 deletions .devops/openvino.Dockerfile
Original file line number Diff line number Diff line change
@@ -1,18 +1,18 @@
ARG OPENVINO_VERSION_MAJOR=2026.2.1
ARG OPENVINO_VERSION_FULL=2026.2.1.21919.ede283a88e3
ARG OPENVINO_VERSION_MAJOR=2026.3.1
ARG OPENVINO_VERSION_FULL=2026.3.1.22476.56d9685302d
ARG UBUNTU_VERSION=24.04

# Intel GPU driver versions. https://github.com/intel/compute-runtime/releases
ARG IGC_VERSION=v2.36.3
ARG IGC_VERSION_FULL=2_2.36.3+21719
ARG COMPUTE_RUNTIME_VERSION=26.22.38646.4
ARG COMPUTE_RUNTIME_VERSION_FULL=26.22.38646.4-0
ARG IGC_VERSION=v2.40.13
ARG IGC_VERSION_FULL=2_2.40.13+22418
ARG COMPUTE_RUNTIME_VERSION=26.31.39395.13
ARG COMPUTE_RUNTIME_VERSION_FULL=26.31.39395.13-0
ARG IGDGMM_VERSION=22.10.0

# Intel NPU driver versions. https://github.com/intel/linux-npu-driver/releases
ARG NPU_DRIVER_VERSION=v1.33.0
ARG NPU_DRIVER_FULL=v1.33.0.20260529-26625960453
ARG LIBZE1_VERSION=1.27.0-1~24.04~ppa2
ARG NPU_DRIVER_VERSION=v1.35.0
ARG NPU_DRIVER_FULL=v1.35.0.20260722-29947505341
ARG LIBZE1_VERSION=1.28.2-1~24.04~ppa1

# Optional proxy build arguments
ARG http_proxy=
Expand Down Expand Up @@ -90,6 +90,9 @@ RUN bash -c "source ${OpenVINO_DIR}/setupvars.sh && \
cmake -B build/ReleaseOV -G Ninja \
-DCMAKE_BUILD_TYPE=Release \
-DLLAMA_BUILD_TESTS=OFF \
-DGGML_NATIVE=OFF \
-DGGML_BACKEND_DL=ON \
-DGGML_CPU_ALL_VARIANTS=ON \
-DGGML_OPENVINO=ON && \
cmake --build build/ReleaseOV --parallel "

Expand Down Expand Up @@ -170,7 +173,7 @@ RUN --mount=type=cache,target=/var/cache/intel-npu,sharing=locked \
fi; \
DEB=/var/cache/intel-npu/libze1_${LIBZE1_VERSION}_amd64.deb; \
if [ ! -f "$DEB" ]; then \
wget -q -O "$DEB" https://snapshot.ppa.launchpadcontent.net/kobuk-team/intel-graphics/ubuntu/20260324T100000Z/pool/main/l/level-zero-loader/libze1_${LIBZE1_VERSION}_amd64.deb; \
wget -q -O "$DEB" https://snapshot.ppa.launchpadcontent.net/kobuk-team/intel-graphics/ubuntu/20260606T100000Z/pool/main/l/level-zero-loader/libze1_${LIBZE1_VERSION}_amd64.deb; \
fi; \
mkdir /tmp/npu/ && cd /tmp/npu/ && tar -xf "$TGZ" && cp "$DEB" .; \
apt-get update; \
Expand Down
2 changes: 1 addition & 1 deletion .github/ISSUE_TEMPLATE/config.yml
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
blank_issues_enabled: true
blank_issues_enabled: false
contact_links:
- name: Got an idea?
url: https://github.com/ggml-org/llama.cpp/discussions/categories/ideas
Expand Down
95 changes: 95 additions & 0 deletions .github/actions/ccache-buckets/action.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,95 @@
name: "ccache-buckets"
description: "Save/restore latest GitHub Actions ccache matching a key prefix to/from HF buckets"
inputs:
key:
description: "Cache key prefix to match and load"
required: true
folder:
description: "Bucket folder containing ccache files"
required: true
evict-old-files:
description: "Corresponds to the ccache --evict-older-than AGE option, where AGE is the number of seconds or days followed by the 's' or 'd' suffix respectively."
default: ''
save:
description: "Save ccache"
required: false
default: false
type: boolean
hf_bucket:
description: 'Hugging Face buckets path'
required: true

runs:
using: "composite"
steps:
- name: Install Hugging Face Hub CLI
shell: bash
run: |
python3 -m venv .venv-hf
.venv-hf/bin/pip install -U huggingface_hub==1.28.0

- name: Restore ccache from buckets
if: ${{ inputs.save != 'true' }}
shell: bash
run: |
set +e -uo pipefail
source .venv-hf/bin/activate
CCACHE_DIR=$(ccache -k cache_dir)
if [[ -d "$CCACHE_DIR" ]]; then
CACHE_PATH=$(hf buckets list "hf://buckets/${{ inputs.hf_bucket }}/${{ inputs.folder }}" --json | jq -r '[.[] | select(.type == "file") | select(.path | startswith("${{ inputs.folder }}/${{ inputs.key }}") and endswith(".tar.gz"))] | sort_by(.path) | last | .path // ""')
if [[ -n "$CACHE_PATH" ]]; then
echo "Restoring ccache from '$CACHE_PATH'."
hf buckets cp "hf://buckets/${{ inputs.hf_bucket }}/$CACHE_PATH" ccache_bucket.tar.gz
mkdir -p ccache_bucket
if tar -xzf ccache_bucket.tar.gz -C ccache_bucket; then
rm -rf "$CCACHE_DIR"
mv ccache_bucket "$CCACHE_DIR"
ccache -z
fi
rm ccache_bucket.tar.gz
else
echo "No ccache found."
fi
else
echo "'$CCACHE_DIR' not found."
fi

- name: Save ccache to buckets
if: ${{ inputs.save == 'true' }}
shell: bash
run: |
if [[ -n "$HF_TOKEN" ]]; then
set +e -uo pipefail
source .venv-hf/bin/activate
CCACHE_DIR=$(ccache -k cache_dir)
if [[ -d "$CCACHE_DIR" ]]; then
ccache -s
if [[ -n "${{ inputs.evict-old-files }}" ]]; then
ccache --evict-older-than "${{ inputs.evict-old-files }}"
fi
DATESTAMP=$(date -u +'%Y-%m-%dT%H:%M:%SZ')
CACHEFILE="${{ inputs.key }}-$DATESTAMP.tar.gz"
if tar -czf ccache_bucket.tar.gz -C "$CCACHE_DIR" .; then
hf buckets cp ccache_bucket.tar.gz "hf://buckets/${{ inputs.hf_bucket }}/${{ inputs.folder }}/$CACHEFILE"
fi
rm ccache_bucket.tar.gz
else
echo "'$CCACHE_DIR' not found."
fi
fi

- name: Remove old ccache files from buckets
if: ${{ inputs.save == 'true' }}
shell: bash
run: |
if [[ -n "$HF_TOKEN" ]]; then
set +e -uo pipefail
source .venv-hf/bin/activate
CACHE_FILES=$(hf buckets list "hf://buckets/${{ inputs.hf_bucket }}/${{ inputs.folder }}" --json | jq -r '[.[] | select(.type == "file") | select((.uploaded_at | .[:19]+"Z" | fromdateiso8601) < (now - 5 * 60)) | select(.path | startswith("${{ inputs.folder }}/${{ inputs.key }}") and endswith(".tar.gz"))] | sort_by(.path)[:-1] | .[] | [.path // ""] | @tsv')
if [[ -n "$CACHE_FILES" ]]; then
echo "Removing old ccache files..."
while IFS=$'\t' read -r CACHE_PATH; do
hf buckets rm "hf://buckets/${{ inputs.hf_bucket }}/$CACHE_PATH" -y
done <<< "$CACHE_FILES"
fi
fi
48 changes: 38 additions & 10 deletions .github/actions/ccache-clear/action.yml
Original file line number Diff line number Diff line change
@@ -1,22 +1,50 @@
# note: place this as the last step of the job, so the new cache is saved by "Post ccache" right after the old one is cleared
name: "ccache-clear"
description: "Delete all GitHub Actions caches matching a key prefix"
description: "Delete GitHub Actions caches matching a key prefix, oldest first"
inputs:
key:
description: "Cache key prefix to match and delete"
required: true
older:
description: "Only delete caches created more than this long ago (e.g. 90m, 1h, 1d). By default all matching caches are deleted"
required: false
default: ""
min:
description: "Stop deleting if fewer than this many caches would remain (e.g. 1). By default there is no minimum"
required: false
default: "0"
dry-run:
description: "Only print the caches that would be deleted, without deleting them"
required: false
default: "false"

runs:
using: "composite"
steps:
- name: Clear caches
- name: Install GitHub CLI if missing
shell: bash
run: |
CACHES=$(gh cache list --key "ccache-${{ inputs.key }}" --json id,key --jq '.[] | "\(.id) \(.key)"' 2>/dev/null)
if [ -z "$CACHES" ]; then
echo "No caches found with key prefix: ${{ inputs.key }}"
exit 0
# e.g. in container jobs, where it is not preinstalled
if ! command -v gh >/dev/null 2>&1; then
echo "GitHub CLI not found, installing..."
if ! command -v curl >/dev/null 2>&1; then
apt-get update >/dev/null 2>&1 || true
apt-get install -y curl >/dev/null 2>&1 || true
fi
mkdir -p -m 755 /etc/apt/keyrings
curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg | tee /etc/apt/keyrings/githubcli-archive-keyring.gpg >/dev/null
chmod go+r /etc/apt/keyrings/githubcli-archive-keyring.gpg
echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" > /etc/apt/sources.list.d/github-cli.list
apt-get update >/dev/null 2>&1 || true
apt-get install -y gh || { echo "Failed to install GitHub CLI (gh)" >&2; exit 1; }
fi
while read -r id key; do
echo "Deleting cache: $id ($key)"
gh cache delete "$id"
done <<< "$CACHES"
command -v gh >/dev/null 2>&1 || { echo "GitHub CLI (gh) is required but could not be installed" >&2; exit 1; }

- name: Clear caches
shell: bash
run: |
bash scripts/ccache-clear.sh \
--key "${{ inputs.key }}" \
--older "${{ inputs.older }}" \
--min "${{ inputs.min }}" \
${{ inputs.dry-run == 'true' && '--dry-run' || '' }}
20 changes: 0 additions & 20 deletions .github/actions/linux-setup-vulkan/action.yml

This file was deleted.

3 changes: 1 addition & 2 deletions .github/actions/windows-setup-cuda/action.yml
Original file line number Diff line number Diff line change
Expand Up @@ -6,8 +6,7 @@ inputs:
required: true
cuda_arch:
description: "CUDA target architecture"
required: false
default: "x64"
required: true

runs:
using: "composite"
Expand Down
2 changes: 1 addition & 1 deletion .github/actions/windows-setup-rocm/action.yml
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ runs:
write-host "Installing ROCm wheels for multi-arch support"
# Install ROCm wheels for multi-arch support (this may take several minutes)
python -m pip install --index-url https://repo.amd.com/rocm/whl-multi-arch/ "rocm[libraries,devel]==${{ inputs.version }}"
python -m pip install --index-url https://stable.repo.amd.com/rocm/whl-next/ "rocm[libraries,devel]==${{ inputs.version }}"
# Pre-expand the devel tree so it is included in the cache
write-host "Initializing ROCm devel tree"
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/build-android.yml
Original file line number Diff line number Diff line change
Expand Up @@ -110,7 +110,7 @@ jobs:
# cache on: https://github.com/ggerganov/tmp2/actions/runs/26534713799/job/78224189394
#
#- name: ccache
# uses: ggml-org/ccache-action@v1.2.21
# uses: ggml-org/ccache-action@v1.2.24
# with:
# key: android-ubuntu-arm64
# evict-old-files: 1d
Expand Down
Loading