Repository navigation

Merge upstream PR #25731: TML Inkling architecture (+ upstream master sync) - #33

Merged

Vect0rM merged 389 commits into

feature/turboquant-kv-cachefrom

inkling-support

Jul 17, 2026

This pull request is big! We're only showing the most recent 250 commits

Commits on Jun 23, 2026

vulkan: Support GET_ROWS_BACK (#24883)
jeffbolznv
authored
92e854a
vulkan: support all backend tests for SQR/SQRT/SIN/COS/CLAMP/LEAKY_RELU/NORM (#24582)
jeffbolznv
authored
72a9269
server : check draft context creation error (#24922)
Kononnable
authored
be4a6a6

Commits on Jun 24, 2026

Commits on Jun 25, 2026

chat: harden caps check (#24973)
pwilkin
authored
09cedfd
opencl: support non-contig rows in norm (#24965)
lhez
authored
fdb2c11
sycl : fix the failed UT cases of conv_3d (#24900)
arthw
authored
9c10954
sycl : support --split-mode tensor (#24152)
Spruill-1
authored
e9fb3b3
quant : fix quantizing moe with mtp (#24986)
CISC
authored
b3ce5ce
build: include libmtmd in Apple XCFramework (#21935)

theabecaster
and
Abraham Gonzalez
authored
e12a012
tests : synchronize contexts at end of test-thread-safety (#24935)
krystophny
authored
fdbd6ab
ui: fix always-show-sidebar-on-desktop setting after navigation refactor (#24979)
ServeurpersoCom
authored
3e61ea0
ggml : address integer overflows in binary ops CUDA implementation (#24706)

fairydreaming
and
sszymczy
authored
f728ada
app : add the llama download subcommand (#24982)
angt
authored
683b04c
docs : Eagle3 qwen3 draft model support (#24977)
kashif
authored
e8ecce5
common: refactor model handling (#24980)
ngxson
authored
60bc886
misc: update lables (#24920)
ngxson
authored
099bf06
server: use status code 403 for disabled features (#24970)
ngxson
authored
e9d1b76
misc: fix labeler (#25012)
ngxson
authored
c7cddef
CUDA: Various fixes to `cpy.cu` (#25000)
ORippler
authored
1ec44d1
model : Add label for LFM2.5-230M (#25008)
tdakhran
authored
9d5d882
xcframework : disable mtmd video on i/tv/visionos (#25018)
CISC
authored
beac530

Commits on Jun 26, 2026

Commits on Jun 27, 2026

tests : fix test-chat-template --no-common option (#25075)
CISC
authored
83d385b
ci : add windows-openvino to check-release (#25022)
CISC
authored
0275c0f
binaries : Improve rpc-server and export-graph-ops names. (#25045)
ckastner
authored
c299a92
vulkan: fix step operator for 0 input (#25036)
0cc4m
authored
0b6529d
sycl : fix failed ut cases of norm (#25044)
arthw
authored
9bebfcb
[CUDA] Added a cudaMemcpy2DAsync fast path to ggml_cuda_cpy (#25057)
gaugarg-nv
authored
0ed235e
opencl: flash attention improvement (#25069)

wanghqc
and
lhez
authored
ebd048f

Commits on Jun 28, 2026

logs : reduce v2 (#25078)
ggerganov
authored
27c8bb4
common : allow --offline in llama download (#25091)
angt
authored
c1a1c8e
spec : add DFlash support (#22105)

ruixiang63
and
kashif
authored
d1b3425
jinja: add --dump-prog for debugging (#25086)

ngxson
and
CISC
authored
f68a788
chat : implement minicpm5 parser (#24889)

aldehir
and
zhangtao
authored
c818263
dflash: refactor draft model conversion (#25110)
ruixiang63
authored
fa72bc6
ui: fix stop and reasoning skip in single-model mode (#25084)
ServeurpersoCom
authored
7cb8576
Revert "ui: fix accessibility for hover-gated interactive elements assisted by claude(in debugging and tests) (#24727)" (#25098)
allozaur
authored
dbdaece
jinja, chat: add --reasoning-preserve flag (#25105)
ngxson
authored
b3fed31

Commits on Jun 29, 2026

Commits on Jun 30, 2026

Commits on Jul 1, 2026

Commits on Jul 2, 2026

llama : add llama_model_ftype_name() (#25134)
angt
authored
fdb1db8

Commits on Jul 3, 2026

Commits on Jul 4, 2026

Commits on Jul 5, 2026

Commits on Jul 6, 2026

Commits on Jul 7, 2026

Commits on Jul 8, 2026

Commits on Jul 9, 2026

hexagon: add VISION RoPE support (#25216)
aparmp-quic
authored
f2d1c2f
server : respect min-step when splitting prompt batches (#25420)
aldehir
authored
64c8b7d
cuda: align snake fusion matcher with the other backends (#25460)
ServeurpersoCom
authored
2021515
ggml-hip: enable -funsafe-math-optimizations (#24668)

RapidMark
and
Mark Caldwell
authored
ccb0c34
metal : add CONV_2D_DW (depthwise convolution) support (#21565)

Sou-ly
and
ggerganov
authored
92b187c
llama-bench : init params.offline (#25476)
angt
authored
259f2e2
Only index by compile times + always multiply/add (#25445)
ORippler
authored
683f0c7
Refactor: Consistently use smart pointers in `test-backend-ops` (#25440)
ORippler
authored
f84a519
meta: add hard emphasis on agents not writing descriptions/comments (#25480)
pwilkin
authored
c15c5c7
ggml : fix conv 2d dw (#25490)
ggerganov
authored
5c3a586
server : move chat-template thinking probe inside the init try/catch (#24093)
palios-taey
authored
82fce65
hexagon: tiling, tracing and optimizations for unary ops (#25474)

aparmp-quic
and
max-krasnyansky
authored
fb30ba9
cli: add --output option (#25484)
ngxson
authored
3de7dd4
ggml : process data in smaller chunks in CUDA ggml_top_k() and ggml_argsort() to reduce temporary buffers memory usage (#24776)

authored
0749449
opencl: cluster-parallel decode FA for Adreno (#25473)
wanghqc
authored
049326a

Commits on Jul 10, 2026

llama-batch: add unit test (#25471)
am17an
authored
961e4b2
ggml-et: Initial ET backend (#24179)

authored
082b326
llama : make all KQ masks f16 if FA is used, remove zero attention bias, remove raw_k repeats in DeepSeek V4 (#25370)

fairydreaming
and
sszymczy
authored
2ed3c1a
ui: export full message tree instead of active path only (#25501)
ServeurpersoCom
authored
d46786f
sync : ggml (#25517)
ggerganov
authored
8f114a9
ui: prevent tooltip from flickering open and closed on hover (#25503)
ServeurpersoCom
authored
c7af942
cli: fix crash on wrong server base url (#25497)
marcoStocchi
authored
1b9691b
server: improve tools, remove apply_diff (#25498)
ngxson
authored
c4ae9a8
ggml : use ggml_vqtbl1q_u8 for 32-bit compat (whisper/0)
ggerganov
committed
ac17f8a
sync : ggml
ggerganov
committed
0badc06
server: remove loading.html (#25500)
ngxson
authored
a935fbf
ui: use server modalities in non-router mode (#24874)
coder543
authored
9f623c6
feat: pre-select models in the webui using alias (#25492)

felix314159
and
example name
authored
07d9378
mtmd: deepseek-ocr v1 multi-tile (#24717)

ngxson
and
sfallah
authored
3e706dd
arg: prevent duplicate spec model downloads (#25527)
ngxson
authored
22b69b6
hexagon: improve ARGSORT performance for small tensors (#25512)
max-krasnyansky
authored
67776ea
llama : make tensor-split regex patterns static (#24710)
eduardopessin
authored
c749cb0
server: accept null sampling params (#25538)
ServeurpersoCom
authored
4f37f51

Commits on Jul 11, 2026

Commits on Jul 12, 2026

Commits on Jul 13, 2026

ui: Remove recommended MCP Servers + improve MCP Servers Settings UI/UX (#25535)
allozaur
authored
38fd5c9
sycl: add Q2_K to DMMV reorder path (#25064)
malsbat
authored
e474bba
sycl: add fused top-k MoE (#25217)

newjordan
and
claude
authored
efb3036
chat : fix reasoning leak with force-opened bare <think> templates (#24674)

newjordan
and
aldehir
authored
91c631b
gguf : add tensor shape accessor (#24405)
QuintinShaw
authored
ad8d821
tests: Harmonize header use (#25616)
ckastner
authored
f4253ef
readme : add link to maintainer PRs (#25621)
ggerganov
authored
4193ea6
spec: add Minimax2 eagle3 support

adrianisk
and
ggerganov
authored
259ae1d
vulkan: Use native e2m1 and e4m3 conversions for mxfp4/nvfp4 (#25338)
jeffbolznv
authored
e920c52
CUDA: refactor MMQ kernel configuration (#24127)
JohannesGaessler
authored
6eddde0
model: add Hy3 (hy_v3) support with MTP speculative decoding (#25395)

authored
2969d6d

Commits on Jul 14, 2026

Commits on Jul 15, 2026

Commits on Jul 16, 2026

Add TML Inkling architecture
danielhanchen
committed
a015409

Commits on Jul 17, 2026

Merge branch 'pr-inkling' into inkling-support
worthant
committed
1d2438f
docs : add MERGE_NOTES.md for the pr-inkling merge
worthant
committed
714fefd
cuda : restore host-staged cross-device copy helpers lost in inkling merge
worthant
committed
807cc6e