Commit Graph

Select branches

Hide Pull Requests

mtp-turboquant

Mono Color

• d0a6a31470 model : add support for JinaBertModel with non-gated ffn (#18475) o7si 2026-01-02 01:38:51 +08:00
• 2b2afade9f convert : fix encoding of WPM vocab for BERT models (#18500) o7si 2026-01-02 01:27:07 +08:00
• f4f5019254 model: add Solar Open model (#18511) HelloKS 2026-01-02 02:01:43 +09:00
• d5574c919c webui: fix code copy stripping XML/HTML tags (#18518) Anri Lombard 2026-01-01 14:44:11 +02:00
• 26831bded9 ggml-cuda: remove unneccesary prints on ggml_cuda_init (#18502) Aman Gupta 2026-01-01 19:18:43 +08:00
• be47fb9285 vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron (#18295) Jeff Bolz 2026-01-01 01:58:27 -06:00
• 9e10bd2eaf llama: handle short reads in direct I/O path (#18504) triplenom 2025-12-31 21:24:43 -05:00
• 4cd162a123 chat: make tool description and parameters optional per OpenAI spec (#18478) Anri Lombard 2026-01-01 01:21:37 +02:00
• 13814eb370 sync : ggml Georgi Gerganov 2025-12-31 18:27:54 +02:00
• 54f67b9b66 ggml : bump version to 0.9.5 (ggml/1410) Georgi Gerganov 2025-12-31 18:24:07 +02:00
• 33ded988ba quantize: prevent input/output file collision (#18451) Anri Lombard 2025-12-31 17:29:03 +02:00
• 0db8109849 convert : lint fix (#18507) Sigbjørn Skjæret 2025-12-31 14:28:21 +01:00
• 9b8329de7a mtmd : Adding support for Nvidia Music Flamingo Model (#18470) Henry147147 2025-12-31 06:13:23 -05:00
• 9a6369bb60 metal : add count_equal op (#18314) gatbontonpc 2025-12-31 00:39:48 -08:00
• ecc343de63 CUDA: fix KQ max calculation (#18487) Johannes Gäßler 2025-12-31 09:37:00 +01:00
• 01ade96e71 metal : remove BF16 x F16 kernels (#18456) Georgi Gerganov 2025-12-31 09:53:48 +02:00
• 7bcaf815c2 sycl: add newline at the end of CMakeLists.txt (#18503) Aman Gupta 2025-12-31 14:23:44 +08:00
• c8a3798041 Work around broken IntelSYCLConfig.cmake in Intel oneAPI 2025.x (#18345) Rahul Sathe 2025-12-31 06:38:44 +05:30
• 4849661d98 docker : add CUDA 13.1 image build (#18441) Sigbjørn Skjæret 2025-12-30 22:28:53 +01:00
• 6e0c8cbc40 docs : document that JSON Schema is not available to model when using response_format (#18492) Bart Louwers 2025-12-30 22:13:49 +01:00
• 0f89d2ecf1 common : default content to an empty string (#18485) Aldehir Rojas 2025-12-30 12:00:57 -06:00
• ac1d0eb7bf llama : fix typo in comment in llama-kv-cache.h [no ci] (#18489) Daniel Bevenius 2025-12-30 17:20:14 +01:00
• cd78e57c3a lora: count lora nodes in graph_max_nodes (#18469) Xuan-Son Nguyen 2025-12-30 15:53:12 +01:00
• c32fa21db8 sampling: reuse token data buffer in llama_sampler_sample (#18365) Jay Zenith 2025-12-30 06:27:49 -08:00
• f14f4e421b server: fix files built redundantly (#18474) Jeff Bolz 2025-12-30 06:11:13 -06:00
• 2d6c00a9b8 kleidiai: add and integrate SVE 256-bit vector-length kernel (#18458) Charles Xu 2025-12-30 13:04:53 +01:00
• d77d7c5c06 CUDA: add log line when mxfp4 acceleration is used (#18483) Aman Gupta 2025-12-30 17:40:46 +08:00
• a864fb1c14 model-conversion : use CONVERTED_MODEL for compare-embeddings (#18461) Daniel Bevenius 2025-12-30 10:13:12 +01:00
• 51a48720b8 webui: fix prompt progress ETA calculation (#18468) Xuan-Son Nguyen 2025-12-29 21:42:11 +01:00
• c9a3b40d65 Webui/prompt processing progress (#18300) Pascal 2025-12-29 19:32:21 +01:00
• 0bd1212a43 CUDA: fix replacment of bad archs in CMake (#18457) Johannes Gäßler 2025-12-29 17:58:20 +01:00
• 5b1248c9af server : Cmdline arg -to changes http read timeout from current 600sec default (#18279) wbtek 2025-12-30 01:12:48 +09:00
• 3595ae5963 contributing: tighten AI usage policy (#18388) Xuan-Son Nguyen 2025-12-29 16:01:32 +01:00
• c1366056f6 android: routine maintenance - Dec 2025 (#18338) Naco Siren 2025-12-29 05:51:13 -08:00
• 2a85f720b8 server : handle closed connection for tasks (#18459) Georgi Gerganov 2025-12-29 15:34:41 +02:00
• 7cbec34a63 model-conversion : add device option to embd run orig model (#18386) Daniel Bevenius 2025-12-29 13:37:02 +01:00
• 0c8986403b retrieval : use at most n_seq_max chunks (#18400) Héctor Estrada Moreno 2025-12-29 05:21:13 -06:00
• daa242dfc8 common: fix return value check for setpriority (#18412) o7si 2025-12-29 17:07:49 +08:00
• e70e640db3 CUDA: Blackwell features for non-native builds (#18436) Johannes Gäßler 2025-12-29 09:35:42 +01:00
• 5fa66c6e67 cuda: fix race condition in cumsum (#18448) Aman Gupta 2025-12-29 14:07:17 +08:00
• 382808c14b ci : re-enable rocm build on amd64 (#18439) Tim Neumann 2025-12-29 00:29:23 +01:00
• 4ffc47cb20 HIP: Use mmq on MFMA devices for MUL_MAT_ID in cases where a lot of splits would be generated (#18202) uvos 2025-12-28 20:12:55 +01:00
• 9c675c7140 model : Plamo3 support (#17304) momonga 2025-12-29 01:28:31 +09:00
• 07a0c4ba92 Revert "ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON (#18413)" (#18426) Aman Gupta 2025-12-28 20:53:36 +08:00
• 60f17f56da rpc: fix segfault on invalid endpoint format (#18387) o7si 2025-12-28 18:34:41 +08:00
• f8d561eb87 llama-fit-params: fix step size for last device (#18415) Johannes Gäßler 2025-12-28 10:52:09 +01:00
• e59efe6a78 github: update issue templates [no ci] (#18410) Johannes Gäßler 2025-12-28 10:50:56 +01:00
• cffa5c46ea mtmd: clarify that we no longer accept AI-generated PRs (#18406) Xuan-Son Nguyen 2025-12-28 09:57:04 +01:00
• 94de74e7b1 cmake: Added more x86_64 CPU backends when building with GGML_CPU_ALL_VARIANTS=On (#18186) Boian Berberov 2025-12-28 07:33:29 +00:00
• 4fd59e8427 ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON (#18413) QDelta 2025-12-27 20:33:14 -05:00
• 08566977a7 opencl: allow resizing transpose buffers (#18384) lhez 2025-12-27 15:51:14 -08:00
• a4bf35889e llama-fit-params: fix overflow check (#18354) Johannes Gäßler 2025-12-27 20:20:45 +01:00
• 026d2ad472 llama: fix magic number of 999 for GPU layers (#18266) Johannes Gäßler 2025-12-27 20:18:35 +01:00
• 06705fdcb3 ggml-cuda: Use same regex for GGML_NATIVE=OFF (#18407) Aman Gupta 2025-12-27 19:56:27 +08:00
• a52dc60ba3 llama_fit_params: return enum for fail vs. error (#18374) Johannes Gäßler 2025-12-27 09:59:19 +01:00
• 9045c9afe5 llama-fit-params: fix Gemma 3 calculation (#18372) Johannes Gäßler 2025-12-27 09:56:04 +01:00
• c9ced4910b vulkan: preprocess mul_mat_id experts and discard workgroups more quickly (#18352) Jeff Bolz 2025-12-26 16:12:58 -06:00
• 7ac8902133 vulkan: optimize decodeFuncB in coopmat2 mul_mat_id shader (#18349) Jeff Bolz 2025-12-26 11:15:50 -06:00
• 9bf20d8ac3 vulkan: Use BK=32 for coopmat2 mul_mat_id (#18332) Jeff Bolz 2025-12-26 11:15:02 -06:00
• cb999704fb vulkan: small dequantization improvements (#18380) Eve 2025-12-26 17:12:11 +00:00
• b96b82fc85 vulkan: Support UPSCALE w/antialias (#18327) Jeff Bolz 2025-12-26 10:00:57 -06:00
• 10dc500bdb vulkan: handle rope with large number of rows (#18306) Jeff Bolz 2025-12-26 09:53:46 -06:00
• 4893cc07bb server : fix crash when seq_rm fails for hybrid/recurrent models (#18391) o7si 2025-12-26 23:35:29 +08:00
• af3be131c0 docs: added note for pre SYCL Intel hardware (#18016) Francisco Herrera 2025-12-25 21:34:30 -05:00
• b07cda687c CANN: implement the SSM_CONV operator (#17737) 0Marble 2025-12-26 09:12:04 +08:00
• 85c40c9b02 ggml-cuda: fix regex for arch list (#18371) Aman Gupta 2025-12-26 01:35:14 +08:00
• 83b3b1c271 cuda: optimize cumsum cub path (#18362) Aman Gupta 2025-12-25 23:55:38 +08:00
• b0fb0f0aee ggml-cuda: fix blackwell native builds (#18361) Aman Gupta 2025-12-25 22:12:11 +08:00
• e68c19b0fd CANN: Add support for CONV_TRANSPOSE_1D when kernel size > 255 (#17934) Penglin Cai 2025-12-25 16:46:09 +08:00
• c54bba869d ggml : optimize cuda cumsum fallback kernel (#18343) Aadeshveer Singh 2025-12-25 09:41:13 +05:30
• f5acfb2ffa server: (router) add stop-timeout option (#18350) Xuan-Son Nguyen 2025-12-24 23:47:49 +01:00
• 4cbafad4f0 model: support MiMo-V2-Flash (#18328) Xuan-Son Nguyen 2025-12-24 23:07:08 +01:00
• c184284230 fit-params : fix race condition in fit-params output (#18276) Aadeshveer Singh 2025-12-24 20:27:38 +05:30
• c8a2417d7b CUDA: experimental native mxfp4 support for blackwell (#17906) Aman Gupta 2025-12-24 22:28:26 +08:00
• 54132f1b1f model : support for LlamaBidirectionalModel architecture (#18220) Saba Fallah 2025-12-24 14:02:36 +01:00
• 2a9ea2020c vulkan: fix command buffer corruption in ggml_backend_vk_event_wait (#18302) Jeff Bolz 2025-12-24 05:36:34 -06:00
• ce7a6dc0fc CANN : refactor ACL graph cache (#17752) Wang Weixuan 2025-12-24 17:50:24 +08:00
• 1ce0126b18 docs: Fix typos in SYCL documentation (#18269) Jesse Ikonen 2025-12-24 11:19:47 +02:00
• 7f459c98e7 vulkan: use fewer FA rows for small cache runs (#18280) Ruben Ortlam 2025-12-24 08:59:14 +01:00
• cf2ffc02bc CANN: Uses yarn_ramp cache in ROPE (#17725) TianHao324 2025-12-24 14:55:33 +08:00
• 10355dc7d0 common: add LLAMA_ARG_OVERRIDE_TENSOR env var for -ot arg (#18267) ddh0 2025-12-24 00:19:12 -06:00
• 5ee4e43f26 server: return_progress to also report 0% processing state (#18305) Xuan-Son Nguyen 2025-12-23 21:49:05 +01:00
• 5b6c9bc0f3 webui: apply webui_settings on first load (#18223) Pascal 2025-12-23 15:48:03 +01:00
• 849d021104 server: fix crash with model not having BOS/EOS (#18321) Xuan-Son Nguyen 2025-12-23 14:39:36 +01:00
• 8e3ead6e4d model-conversion : add device option to run-org-model.py (#18318) Daniel Bevenius 2025-12-23 14:07:25 +01:00
• 12ee1763a6 rpc : add check for rpc buffer type (#18242) Chris Rohlf 2025-12-23 04:56:49 -05:00
• ed75977717 ggml-hexagon: create generalized functions for cpu side op (#17500) nullname 2025-12-23 15:13:24 +08:00
• 847c35f7d5 model-conversion : add trust_remote_code for embedding scripts (#18288) Daniel Bevenius 2025-12-23 07:27:37 +01:00
• a6a552e4ec [SYCL] replace llama-cli by llama-completion to rm the impact to test script (#18290) Neo Zhang 2025-12-23 12:59:12 +08:00
• 96e33a814e model : fix div-by-zero for Nemotron V2 (#18309) Alessandro98-git 2025-12-23 03:04:57 +01:00
• dfc959b886 model : Granite Embedding support (#15641) Ryan Mangeno 2025-12-22 18:28:19 -05:00
• 8f48807380 gguf-py : do not align the data start offset (#18291) compilade 2025-12-22 14:25:16 -05:00
• bf6bc3c155 ggml-hexagon: gelu optimization (#18151) Shouyu 2025-12-22 13:56:52 -05:00
• 179fd82a72 gen-docs: automatically update markdown file (#18294) Xuan-Son Nguyen 2025-12-22 19:30:19 +01:00
• d34d5ca1e9 llamafile: add rvv support for sgemm kernels (#18199) Taimur Ahmad 2025-12-22 23:20:23 +05:00
• eb492bf43f opencl: unpack q4_0 for adreno in get_tensor (#18278) lhez 2025-12-22 10:19:01 -08:00
• e3b35ddf1c vulkan: Extend rope fusions to allow mrope (#18264) Jeff Bolz 2025-12-22 11:03:13 -06:00
• 6ce863c803 server: prevent data race from HTTP threads (#18263) Xuan-Son Nguyen 2025-12-22 14:23:34 +01:00
• 3997c78e33 server: fix data race in to_json_anthropic (#18283) Xuan-Son Nguyen 2025-12-22 13:21:43 +01:00
• ee74642982 release: update release workflow to store XCFramework as Zip file (#18284) Mattt 2025-12-22 04:11:46 -08:00