upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-28 13:41:01 -05:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • c556418b60 llama-bench : use local GPUs along with RPC servers (#14917) b6017 Radoslav Gerganov 2025-07-28 18:59:04 +03:00
  • db16e2831c ggml-cpu : deduplicate scalar implementations (#14897) b6016 xctan 2025-07-28 23:40:24 +08:00
  • cd1fce6d4f SYCL: Add set_rows support for quantized types (#14883) b6015 Akarshan Biswas 2025-07-28 20:32:15 +05:30
  • 00fa15fedc mtmd : add support for Voxtral (#14862) b6014 Xuan-Son Nguyen 2025-07-28 15:01:48 +02:00
  • 946b1f6859 CUDA: fix pointer incrementation in FA (#14916) b6013 Johannes Gäßler 2025-07-28 14:30:22 +02:00
  • 477d43988a repack : optimize mul_mat_id path Georgi Gerganov 2025-07-28 15:19:04 +03:00
  • 6c6e397aff model : add support for SmallThinker series (#14898) b6012 Dongliang Wei 2025-07-28 19:47:00 +08:00
  • afc0e89698 sycl: refactor quantization to q8_1 (#14815) b6011 Alberto Cabrera Pérez 2025-07-28 11:05:53 +01:00
  • a5771c9eea ops : update BLAS (#14914) Georgi Gerganov 2025-07-28 11:01:03 +03:00
  • e9f7e7cce2 ops : update BLAS gg/ops-update-blas Georgi Gerganov 2025-07-28 09:42:57 +03:00
  • c35f9eaf09 ops : update Metal (#14912) Georgi Gerganov 2025-07-28 08:22:56 +03:00
  • 1f45f2890e sync : ggml Georgi Gerganov 2025-07-28 08:14:20 +03:00
  • 613c5095c3 cmake : Indent ggml-config.cmake (ggml/1310) Kai Pastor 2025-07-24 19:58:02 +02:00
  • 7f97599581 quantize : update README.md (#14905) Ed Addario 2025-07-27 22:31:11 +01:00
  • e2661edd24 ggml : repack block_iq4_nlx8 Georgi Gerganov 2025-07-26 20:03:43 +03:00
  • bf78f5439e vulkan: add ops docs (#14900) Ruben Ortlam 2025-07-27 15:33:08 +02:00
  • bbfc849274 SYCL: add ops doc (#14901) Akarshan Biswas 2025-07-27 17:52:58 +05:30
  • ca0ef2dddb llama : clarify comment about pp and tg graphs [no ci] (#14895) Daniel Bevenius 2025-07-27 12:10:51 +02:00
  • 89d1029559 vulkan : add fp16 support for the conv_2d kernel (#14872) b6002 Erik Scholz 2025-07-27 12:04:33 +02:00
  • f1a4e72de5 vulkan: skip empty set_rows to avoid invalid API usage (#14860) b6001 Jeff Bolz 2025-07-27 04:05:34 -05:00
  • 4762ad7316 model : make rope_yarn_log_mul optional for deepseek2 (#14896) b6000 Gabriel Larson 2025-07-27 03:18:37 -05:00
  • 1dc9614e06 llama : fix kq_scale for the attention layers of PLaMo2 (#14892) b5999 Shunta Saito 2025-07-27 16:38:44 +09:00
  • 446595b9b3 Docs: add instructions for adding backends (#14889) b5998 Aman Gupta 2025-07-27 09:36:43 +08:00
  • 66906cd82a HIP: Enable Matrix cores for MMQ Kernels, Enable stream-K for CDNA 3 (#14624) b5997 deepsek 2025-07-26 18:28:14 -04:00
  • 11dd5a44eb CANN: Implement GLU ops (#14884) b5996 hipudding 2025-07-26 17:56:18 +08:00
  • 9b8f3c6c77 musa: fix build warnings (unused variable) (#14869) b5995 R0CKSTAR 2025-07-26 10:36:02 +08:00
  • c7f3169cd5 ggml-cpu : disable GGML_NNPA by default due to instability (#14880) b5994 Aaron Teo 2025-07-26 01:09:03 +08:00
  • 793c0d7f46 metal: SSM_SCAN performance (#14743) b5993 Gabe Goodhart 2025-07-25 10:47:39 -06:00
  • ce111d39d6 opencl: add fused rms_norm_mul (#14841) b5992 lhez 2025-07-25 08:12:13 -07:00
  • e7fecba934 docs : update HOWTO‑add‑model.md for ModelBase and new model classes (#14874) wooksong 2025-07-25 23:25:05 +09:00
  • a5801f408f sync : ggml sync-ggml-25-07-25 Georgi Gerganov 2025-07-25 14:31:39 +03:00
  • 2c1f810178 cmake : Indent ggml-config.cmake (ggml/1310) Kai Pastor 2025-07-24 19:58:02 +02:00
  • e2b7621e7c ggml : remove invalid portPos specifiers from dot files (#14838) b5990 Oliver Simons 2025-07-25 13:29:57 +02:00
  • c1dbea752a context : restore preemptive sched reset when LLAMA_SET_ROWS=0 (#14870) b5989 Georgi Gerganov 2025-07-25 14:28:06 +03:00
  • 749e0d27f0 mtmd : fix 32-bit narrowing issue in export-lora and mtmd clip (#14503) b5988 kiwi 2025-07-25 19:08:04 +08:00
  • 64bf1c3744 rpc : check for null buffers in get/set/copy tensor endpoints (#14868) b5987 Chris Rohlf 2025-07-25 06:17:02 -04:00
  • 6f4c57236b server : fix vision test regex gg/server-fix-vision-tests Georgi Gerganov 2025-07-25 11:22:36 +03:00
  • c12bbde372 sched : fix multiple evaluations of the same graph with pipeline parallelism (#14855) b5986 Diego Devesa 2025-07-25 01:07:26 -07:00
  • 3f4fc97f1d musa: upgrade musa sdk to rc4.2.0 (#14498) b5985 R0CKSTAR 2025-07-25 03:05:37 +08:00
  • 2df255da3c sync : ggml b5984 Georgi Gerganov 2025-07-24 18:30:33 +03:00
  • 60f816a79d cmake : fix usage issues (ggml/1257) Kai Pastor 2025-07-22 20:13:21 +02:00
  • 5592f278b6 ggml-cpu : remove stdlib include from repack.cpp (ggml/1276) Daniel Bevenius 2025-07-21 15:53:12 +02:00
  • e65aa69402 context : only sort outputs when needed compilade/output-reorder-lazy-sort Francis Couture-Harpin 2025-07-24 11:06:34 -04:00
  • a124399f19 sched : fix multiple evaluations of the same graph with pipeline parallelism sl/sched-copy-incr-fix slaren 2025-07-24 16:03:14 +02:00
  • e4868d16d2 context : perform output reorder lazily upon access after sync (#14853) b5981 Georgi Gerganov 2025-07-24 16:31:48 +03:00
  • 978c88ba0a cont : add TODO gg/context-sync-upon-output-reorder Georgi Gerganov 2025-07-24 16:31:10 +03:00
  • 820de57d4f chat : fix kimi-k2 chat template (#14852) b5980 Xuan-Son Nguyen 2025-07-24 13:59:56 +02:00
  • 5e58711c28 context : perform output reorder after lazily upon access after sync Georgi Gerganov 2025-07-24 14:28:09 +03:00
  • cb4a63aad6 sycl: fixed semantics of block offset calculation (#14814) b5979 Alberto Cabrera Pérez 2025-07-24 11:09:57 +01:00
  • 86f5623d90 llama : fix MiniCPM inference after Granite Four changes (#14850) b5978 yummy 2025-07-24 17:50:51 +08:00
  • 39cffdf188 docs: add libcurl-dev install hint for Linux distros (#14801) Pouya 2025-07-24 12:26:44 +03:00
  • 065908cb09 metal : fix fusion across different encoders (#14849) b5976 Georgi Gerganov 2025-07-24 10:24:05 +03:00
  • 4ec6291a24 sycl: fix undefined variable in work group size check (#14843) b5975 Donghyeon Jeong 2025-07-24 13:50:41 +09:00
  • 1ef3cc1a87 imatrix : use GGUF regardless of the output filename compilade/imatrix-gguf-default Francis Couture-Harpin 2025-07-23 23:08:03 -04:00
  • 53f65c354e imatrix : use GGUF by default Francis Couture-Harpin 2025-07-23 21:33:53 -04:00
  • a12363bbf0 convert : text-only support for GLM-4.1V-9B-Thinking (#14823) jacekpoplawski 2025-07-23 23:23:57 +02:00
  • a86f52b285 CUDA: fix overflow in FA, tune performance (#14840) b5973 Johannes Gäßler 2025-07-23 21:43:25 +02:00
  • b284197df4 CUDA: fix compilation with GGML_CUDA_F16 (#14837) b5972 Johannes Gäßler 2025-07-23 18:22:30 +02:00
  • 221c0e0c58 ci : correct label refactor->refactoring (#14832) Sigbjørn Skjæret 2025-07-23 14:27:54 +02:00
  • 07a19e27a2 CUDA: fix quantized KV cache + multiple sequences (#14822) b5970 Johannes Gäßler 2025-07-23 12:35:53 +02:00
  • 18f3b5ff9e tests : add non-cont K,V FA tests Georgi Gerganov 2025-07-18 13:36:27 +03:00
  • 7233358d29 memory : handle saving/loading null layers in recurrent memory (#14675) b5968 l3utterfly 2025-07-23 16:16:41 +08:00
  • 6c88b3bb25 ggml: fix loongarch quantize_row_q8_1 error (#14827) b5967 lixing-star 2025-07-23 14:39:51 +08:00
  • 14c28dfc50 CANN: weight format to NZ for Ascend310P3 (#14407) b5966 chen fan 2025-07-23 11:58:00 +08:00
  • 8c988fa41d CUDA: add fused rms norm (#14800) b5965 Aman Gupta 2025-07-23 09:25:42 +08:00
  • bc39aa67f9 examples/finetune -opt SGD (stochastic gradient descent) memory opt graehl 2025-06-09 11:59:37 -07:00
  • 55cf48de1e cuda : fix multi-seq, quantized FA gg/fix-fa-q-non-cont Georgi Gerganov 2025-07-22 20:48:53 +03:00
  • acd6cb1c41 ggml : model card yaml tab->2xspace (#14819) Csaba Kecskemeti 2025-07-22 09:29:43 -07:00
  • 84712b6043 vulkan: fix rms_norm_mul to handle broadcasting dim0 (#14817) b5963 Jeff Bolz 2025-07-22 10:35:21 -05:00
  • d4d1522b20 llama : add model type detection for rwkv7 7B&14B (#14816) b5962 Molly Sophia 2025-07-22 23:01:29 +08:00
  • d1aa0cc5d1 imatrix: add option to display importance score statistics for a given imatrix file (#12718) b5961 Ed Addario 2025-07-22 13:33:37 +01:00
  • c8ade30036 Mtmd: add a way to select device for vision encoder (#14236) b5960 stduhpf 2025-07-22 12:51:03 +02:00
  • e28c0b80c2 cuda : implement bf16 cpy ops and enable bf16 cont (#14763) b5959 Sigbjørn Skjæret 2025-07-22 12:33:10 +02:00
  • de12f8ac50 convert : begin handling pre-quantized models Francis Couture-Harpin 2025-07-22 02:47:34 -04:00
  • 8e6f8bc875 opencl: remove unreachable return (#14806) b5958 lhez 2025-07-21 23:53:30 -07:00
  • adef81781a server : allow setting --reverse-prompt arg (#14799) b5957 Molly Sophia 2025-07-22 09:24:22 +08:00
  • 48b86c4fdb cuda: remove linking to cublasLt (#14790) b5956 R0CKSTAR 2025-07-22 07:45:26 +08:00
  • 38d3af1b73 opencl: fix im2col when KW!=KH (#14803) Sigbjørn Skjæret 2025-07-21 22:55:10 +02:00
  • 6c9ee3b17e opencl: add conv2d kernel (#14403) b5954 rmatif 2025-07-21 19:03:19 +02:00
  • cd465d823c sycl: Fix im2col (#14797) b5953 Romain Biessy 2025-07-21 18:39:29 +02:00
  • 922042601b kleidiai: add support for get_rows (#14676) b5952 Charles Xu 2025-07-21 15:49:52 +02:00
  • 2ba1333b35 docs : fix backends table in README.md (#14796) Radoslav Gerganov 2025-07-21 15:03:49 +03:00
  • c2e058f1b4 vulkan/cuda: Fix im2col when KW!=KH (#14789) b5950 Jeff Bolz 2025-07-21 06:35:40 -05:00
  • c82d48ec23 llama : fix --reverse-prompt crashing issue (#14794) b5949 Molly Sophia 2025-07-21 17:38:36 +08:00
  • b4efd77f8a server : add parse_special option to /tokenize endpoint (#14783) IsaacDynamo 2025-07-21 09:24:51 +02:00
  • 2be60cbc27 docs : fix link for tools/perplexity in README.md (#14780) Aman Gupta 2025-07-21 02:13:47 +08:00
  • b526ad2668 Documentation: Further revisions to the Vulkan section in build.md (#14785) rspOverflow 2025-07-20 23:55:32 +07:00
  • 938b785764 Clang-format: local files first + fix BinPacking (#14779) Aman Gupta 2025-07-20 19:42:34 +08:00
  • 36c153248f Contrib: add 0cc4m as codeowner for Vulkan backend (#14775) 0cc4m 2025-07-19 22:47:21 +02:00
  • a979ca22db ggml: adds CONV_2D op and direct GEMM Vulkan implementation (#14316) b5943 Ervin Áron Tasnádi 2025-07-19 21:59:08 +02:00
  • 73439beb1b imatrix : use a single count for dense 3d tensors Francis Couture-Harpin 2025-07-19 12:57:57 -04:00
  • 90083283ec imatrix : use GGUF to store importance matrices (#9400) b5942 compilade 2025-07-19 12:51:22 -04:00
  • d4b91ea7b2 vulkan: Add logging for bf16 features to ggml_vk_print_gpu_info (#13274) (#14707) b5941 Peter0x44 2025-07-19 16:58:03 +01:00
  • 83f5872404 Vulkan: Fix fprintf format-security warning (#14770) b5940 0cc4m 2025-07-19 17:47:53 +02:00
  • f0d4d176df Documentation: Update build.md's Vulkan section (#14736) rspOverflow 2025-07-19 17:18:36 +07:00
  • b17230917c sync : ggml Georgi Gerganov 2025-07-19 11:46:12 +03:00
  • 386892ec61 sync : ggml sync-ggml-25-07-19 Georgi Gerganov 2025-07-19 11:46:12 +03:00
  • bf9087f59a metal : fuse add, mul + add tests (#14596) b5937 Georgi Gerganov 2025-07-18 20:37:26 +03:00
  • 9fb1042ce6 graph : fix graph reuse reset of params (#14760) b5936 Georgi Gerganov 2025-07-18 20:08:33 +03:00
  • cfe5e98423 graph : fix graph reuse reset of params gg/graph-reuse-reset-fix Georgi Gerganov 2025-07-18 17:50:32 +03:00