This website requires JavaScript.
cb64222b0c
vulkan: support GGML_UNARY_OP_XIELU (#18062 )
2025-12-21 03:17:58 -06:00
6eb7081860
vulkan: in graph_optimize, try to group ADD operations (#18060 )
2025-12-21 03:05:08 -06:00
4117ae5557
Vulkan: some improvement on mul_mat_iq2_xs (#18031 )
2025-12-21 09:59:52 +01:00
65e96a2464
docs : fix links in parsing.md (#18245 )
2025-12-21 09:35:40 +01:00
9496bbb808
common : reorganize includes to prioritize vendored deps (#18222 )
2025-12-20 21:43:21 -06:00
ddcb75dd8a
server: add auto-sleep after N seconds of idle (#18228 )
2025-12-21 02:24:42 +01:00
52ab19df63
tests: Avoid floating point precision false positives in SUM (#17471 )
2025-12-20 13:46:46 -06:00
5182dd64cd
test-backend-ops: improve msvc build time (#18209 )
2025-12-20 13:45:45 -06:00
10b4f82d44
Added comments explaining thread block size selection logic based on row count and column size, derived from historical commit context (#18212 )
2025-12-20 16:58:57 +05:30
408616adbd
server : [easy] fix per round speculative decode logging (#18211 )
2025-12-20 04:57:40 -05:00
9e39a1e6a9
server: support load model on startup, support preset-only options (#18206 )
2025-12-20 09:25:27 +01:00
74e05131e9
ci : remove non-windows zip artifacts (#18201 )
2025-12-19 22:29:46 +01:00
f74747d886
ci : only save ccache on master (#18207 )
2025-12-19 22:29:37 +01:00
ce734a8a2f
ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (#17977 )
2025-12-19 12:42:28 -05:00
14931a826e
arg: fix order to use short form before long form (#18196 )
2025-12-19 18:01:56 +01:00
f99ef53d2a
llama : Changing off_t to size_t for Windows (#18204 )
2025-12-19 15:42:46 +01:00
cc0a04343e
server: friendlier error msg when ctx < input (#18174 )
2025-12-19 19:10:00 +08:00
98c1c7a7bf
presets: refactor, allow cascade presets from different sources, add global section (#18169 )
2025-12-19 12:08:20 +01:00
acb73d8340
webui: Add editing attachments in user messages (#18147 )
2025-12-19 11:14:07 +01:00
0a271d82b4
model-conversion : add verbose flag in run-org-model.py (#18194 )
2025-12-19 08:43:16 +01:00
52fc7fee8a
android: fix missing screenshots for Android.md (#18156 )
2025-12-18 23:32:04 -08:00
cdbada8d10
vulkan: Add perf logger mode with concurrency (#17944 )
2025-12-18 23:36:46 -06:00
8ea958d4d9
model : add ASR support for LFM2-Audio-1.5B (conformer) (#18106 )
2025-12-19 00:18:01 +01:00
f9ec8858ed
webui: display prompt processing stats (#18146 )
2025-12-18 17:55:03 +01:00
f716588e63
ggml-cpu: extend support for RVV floating-point kernels (#17318 )
2025-12-18 19:02:09 +05:00
4d1316c440
arg: fix ASAN error on sampler_type_names empty (#18167 )
2025-12-18 14:30:32 +01:00
ec7b9329ae
gguf-py : use copy-on-write mode for localtensor (#18162 )
2025-12-18 13:45:38 +01:00
54189c0d39
remove i_major_dual (#18157 )
2025-12-18 19:50:56 +08:00
9ce64aed7d
webui: Fix selecting generated output issues during active streaming (#18091 )
2025-12-18 11:13:52 +01:00
900316da4e
webui: fix chat screen shadow width (#18010 )
2025-12-18 11:08:42 +01:00
57c1e05643
llama: offload output layer to GPU first (#18148 )
2025-12-18 08:12:18 +01:00
9cff4cc554
convert : sort and use file parts from model index if present (#18043 )
2025-12-18 07:54:54 +01:00
4d4f4cacd1
llama : Async DirectIO model loading on Linux (#18012 )
2025-12-18 07:27:19 +01:00
0a0bba05e8
ggml-hexagon: swiglu_oai operation (#18114 )
2025-12-17 16:38:21 -05:00
5166aaf868
convert : force patch_merger tensors to f16/f32 (#18124 )
2025-12-17 22:15:53 +01:00
6ce3d85796
server: (webui) add --webui-config (#18028 )
2025-12-17 21:45:45 +01:00
e85e9d7637
server: (router) disable SSL on child process (#18141 )
2025-12-17 21:39:08 +01:00
8dcc3662a2
llama-fit-params: fix memory print (#18136 )
2025-12-17 21:10:03 +01:00
d37fc93505
webui: fix chat header width when sidebar is closed (#17981 )
2025-12-17 20:05:45 +01:00
4470a0764a
ggml-hexagon: gelu operation (#17921 )
2025-12-17 13:39:32 -05:00
4301e27319
common : restore grammar-based rejection sampling (#18137 )
2025-12-17 19:46:00 +02:00
a2c199e479
common: clarify instructions for bug reports (#18134 )
2025-12-17 18:44:13 +01:00
15dd67d869
model: fix GLM-ASR-Nano-2512 load error (#18130 ) (#18142 )
2025-12-17 23:34:35 +08:00
bde461de8c
server: (router) allow child process to report status via stdout (#18110 )
2025-12-17 14:54:11 +01:00
8faa87db02
Extend run-org-model.py, add (a) batching (b) loading prompt from file (c) multimodal capacity (#18034 )
2025-12-17 14:21:51 +01:00
6f1f6a961a
Github: ask for -v logs for params_fit [no ci] (#18128 )
2025-12-17 13:46:48 +01:00
669696e00d
ggml-cpu: ARM64: repack version of q8_0 (dotprod and i8mm) (#18096 )
2025-12-17 11:39:13 +00:00
982060fadc
model: fix LFM2_MOE missing tensors (#18132 )
2025-12-17 12:17:11 +01:00
6853bee680
ci : clean up webui jobs (#18116 )
2025-12-17 10:45:40 +01:00
487674fbb3
common: fix --override-kv to support comma-separated values (#18056 )
2025-12-17 10:36:23 +01:00
acec774ef6
HIP: Refactor mma for RDNA and CDNA (#17990 )
2025-12-17 16:34:54 +08:00
5c0d18881e
llama.android : Rewrite Android binding (w/o cpu_features dep) (#17413 )
2025-12-17 00:14:47 -08:00
4b2a4778f8
arg: allow -kvu flag for llama-perplexity (#18117 )
2025-12-16 22:33:02 -08:00
58062860af
ggml : use WARP_SIZE/2 for argmax reduction offset (#18092 )
2025-12-17 09:17:01 +05:30
2973a65ecb
gguf-py : allow converting multi-tensor models from read-only locations (#18100 )
2025-12-16 20:27:03 -05:00
d0794e89d9
llama-fit-params: force disable mlock (#18103 )
2025-12-17 00:50:12 +01:00
9dcac6cf9f
llama-fit-params: lower ctx size for multi GPU (#18101 )
2025-12-17 00:49:34 +01:00
0e49a7b8b4
llama-fit-params: fix underflow for dense models (#18095 )
2025-12-17 00:47:37 +01:00
4164596c76
llama-fit-params: QoL impr. for prints/errors (#18089 )
2025-12-17 00:03:19 +01:00
ef83fb8601
model: fix LFM2 missing tensors (#18105 )
2025-12-16 19:07:43 +01:00
ec98e20021
llama: fix early stop in params_fit if ctx is set (#18070 )
2025-12-16 14:24:00 +01:00
59977eba7b
server: fix crash when batch > ubatch with embeddings (#17912 )
2025-12-16 07:27:36 -05:00
79dbae034a
model-conversion : remove -fa option in model card template [no ci] (#18088 )
2025-12-16 13:25:09 +01:00
7f2b2f3c77
arch: refactor LLM_TENSOR_NAMES (#18051 )
2025-12-16 13:22:30 +01:00
7b1db3d3b7
arg: clarify auto kvu/np being set on server (#17997 )
2025-12-16 12:01:27 +01:00
a5251ca11d
Optimization: Qwen3 next autoregressive pass (#17996 )
2025-12-16 11:59:53 +01:00
fb644247de
CLI: fixed adding cli and completion into docker containers, improved docs (#18003 )
2025-12-16 13:52:23 +03:00
5f5f9b4637
server: Update README.md incorrect argument (#18073 )
2025-12-16 20:50:43 +10:00
3d86c6c2b5
model: support GLM4V vision encoder (#18042 )
2025-12-16 11:25:26 +01:00
9963b81f63
model-conversion : add note about verifying previous models (#18082 )
2025-12-16 11:17:40 +01:00
db81d5ec4b
model-conversion : use CONVERTED_EMBEDDING_MODEL for embedding_verify_logits (#18079 )
2025-12-16 11:17:20 +01:00
c05aa69f32
common : add nemotron 3 parsing (#18077 )
2025-12-16 04:05:23 -06:00
279cef27c2
added note for old Intel hardware pre sycl (#18017 )
2025-12-16 04:45:09 -05:00
5ba95754ee
security : add collaborator guidance (#18081 )
2025-12-16 11:17:11 +02:00
2aa45ef9e3
llama: Include algorithm header needed for C++23 (#18078 )
2025-12-15 23:37:55 -08:00
c560316440
graph : reuse SSM graphs (#16490 )
2025-12-16 09:36:21 +02:00
d6742125c3
ci : separate webui from server (#18072 )
2025-12-16 08:17:26 +01:00
3034836d36
webui: Improve copy to clipboard with text attachments (#17969 )
2025-12-16 07:38:46 +01:00
a20979d433
webui: Add setting to always show sidebar on Desktop (#17809 )
2025-12-16 07:31:37 +01:00
2995341730
llama : add support for NVIDIA Nemotron 3 Nano (#18058 )
2025-12-16 07:19:26 +01:00
40d9c394f4
Webui: Disable attachment button and model selector button when prompt textbox is disabled. (#17925 )
2025-12-16 01:15:49 -05:00
d6a1e18c65
convert : move rope_parameters to TextModel class (#18061 )
2025-12-15 22:03:16 +01:00
c45f89d551
ggml-hexagon: mm for mtmd (#17894 )
2025-12-15 13:53:56 -05:00
9d52f17ae3
model : add KORMo model (#18032 )
2025-12-16 02:51:43 +09:00
4529c660c8
kv-cache: Fix state restore fragmented cache (#17982 )
2025-12-15 09:28:35 -08:00
0f4f35e7be
Fix unreadable user markdown colors and truncate long texts in deletion dialogs (#17555 )
2025-12-15 16:34:53 +01:00
165caaf5fb
metal: use shared buffers on eGPU (#17866 )
2025-12-15 15:14:49 +01:00
96a181a933
mtmd: refactor audio preprocessing (#17978 )
2025-12-15 14:16:52 +01:00
4a4f7e6550
cli: fixed dead links to tools/main for cli and completion, fixed code owners (#17993 )
2025-12-15 13:47:04 +03:00
e73d548659
webui: add "delete all conversations" button to import/export tab (#17444 )
2025-12-15 11:29:29 +01:00
b1f3a6e5db
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653 )
2025-12-15 09:24:59 +01:00
4aced7a631
[SYCL] Support gpt-oss by OPs add-id, mul_mat for mxfp4, swiglu_oai (#17826 )
2025-12-15 10:35:15 +08:00
745fa0e78b
model : add glm-asr support (#17901 )
2025-12-15 10:18:46 +08:00
52392291b2
preset: handle negated arg, reverse the meaning if needed (#18041 )
2025-12-14 22:08:10 +01:00
5c8a717128
convert : refactor rope scaling handling (#18013 )
2025-12-14 16:04:37 +01:00
37f5a1093b
mtmd: enhance image resizing in llava_uhd (#18014 )
2025-12-14 22:57:52 +08:00
9e6649ecf2
vulkan: fix mul_mat_vec_iq1_s formatting (#18026 )
2025-12-14 14:52:46 +01:00
0759b09c90
graph: add f_attn_temp_offset (#18025 )
2025-12-14 13:05:59 +01:00
254098a279
common : refactor common_sampler + grammar logic changes (#17937 )
2025-12-14 10:11:13 +02:00
3238b1400c
vulkan: Fix data race/hang in scalar/cm1 flash attention (#17887 )
2025-12-14 02:00:00 -06:00
Jeff Bolz