upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-28 21:50:56 -05:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 5630406959 llama-mtmd-cli: Sigint rework in mtmd vision example (#13080) b5174 pl752 2025-04-24 02:32:35 +05:00
  • a06d9a035d media : testing [no ci] Georgi Gerganov 2025-04-23 22:09:23 +03:00
  • ecda2ec4b3 mtmd : Support Pixtral 12B (#13065) b5173 Xuan-Son Nguyen 2025-04-23 20:21:59 +02:00
  • eb1776b15a convert : Append mult-eos,half-rope,bos to GLM4-0414 and Z (#13021) piDack 2025-04-23 22:59:14 +08:00
  • 2cca6c01e4 rpc : add command line option for number of threads for the CPU backend (#13060) b5171 Radoslav Gerganov 2025-04-23 10:32:49 +03:00
  • 658987cfc9 CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID (#13014) b5170 Johannes Gäßler 2025-04-22 21:27:40 +02:00
  • dc39a5e7a8 mtmd : support SmolVLM (version 1 and 2) (#13050) b5169 Xuan-Son Nguyen 2025-04-22 16:24:54 +02:00
  • ab47dec3d3 security : add note about RPC and server functionality (#13061) Georgi Gerganov 2025-04-22 16:16:10 +03:00
  • 7b53389c24 metal : add memory pool for temp allocs (#12850) Georgi Gerganov 2025-04-22 16:15:51 +03:00
  • 243453533e llava : update documentations (#13055) b5166 Xuan-Son Nguyen 2025-04-22 10:37:00 +02:00
  • 1d735c0b4f ggml : add SSE 4.2 and x64 base variant for CPUs without AVX (#12871) b5165 Diego Devesa 2025-04-21 18:13:51 +02:00
  • 5368ddda7a SYCL: Add non-contiguous support in ROPE (#12993) b5164 Akarshan Biswas 2025-04-21 19:13:30 +05:30
  • 84a9bf2fc2 mtmd : merge llava, gemma3 and minicpmv CLI into single llama-mtmd-cli (#13012) b5163 Xuan-Son Nguyen 2025-04-21 15:32:58 +02:00
  • 2016f07bd1 convert : experimental support for --mmproj flag (#13023) b5162 Xuan-Son Nguyen 2025-04-20 23:29:36 +02:00
  • 6602304814 llava: fix errors in clip.h on certain compilers (#13030) b5161 Jeffrey Morgan 2025-04-20 03:15:41 -07:00
  • 66168204be vulkan: support noncontiguous rms_norm (#13031) b5160 Jeff Bolz 2025-04-20 03:50:02 -05:00
  • 4ba9d711ba metal: add neg operator (#13029) b5159 Jeffrey Morgan 2025-04-19 22:28:40 -07:00
  • 00137157fc Disable CI cross-compile builds (#13022) b5158 bandoti 2025-04-19 13:05:03 -03:00
  • fb28f4f80e gguf-py : fix upload python package workflow (#13020) gguf-v0.16.2 Sigbjørn Skjæret 2025-04-19 16:26:38 +02:00
  • 37b9f0d29d clip : refactor, add image_manipulation and llava_uhd classes (#13011) b5156 Xuan-Son Nguyen 2025-04-19 09:15:45 +02:00
  • 6408210082 main : Fix Ctrl+D/newline handling (#12951) b5155 Daniel Tang 2025-04-18 16:02:55 -04:00
  • aff9d107b0 gguf-py : GGUF Editor GUI - Python + Qt6 (#12930) gguf-v0.16.1 Chris Thompson 2025-04-18 12:30:41 -06:00
  • 35370ba945 server : use std::move whenever possible (#12936) b5153 Xuan-Son Nguyen 2025-04-18 19:58:12 +02:00
  • 8d66005763 SYCL: Refactor and enable FP16 in binary broadcast OPs (#12975) b5152 Akarshan Biswas 2025-04-18 19:27:56 +05:30
  • b9154ecff9 mtmd : add methods to access mtmd_image_tokens (#12906) b5151 Xuan-Son Nguyen 2025-04-18 10:04:51 +02:00
  • 2db9ba1464 rpc : add RPC_CMD_HELLO (#12955) b5150 Radoslav Gerganov 2025-04-18 10:13:42 +03:00
  • 2f74c354c0 graph : make FA compatible with MLA + add initial Metal kernels (#12953) b5149 Georgi Gerganov 2025-04-17 18:16:36 +03:00
  • 207c22ec2d ggml: Re-enable CUDA graphs in presence of CONT and DUP nodes (#12970) b5148 Alan Gray 2025-04-17 14:19:42 +01:00
  • 7a395f67a7 CANN: Add support for async operator submission (#12864) b5147 hipudding 2025-04-17 20:34:16 +08:00
  • 971f245b3b llama : recognize IBM Granite 3.3 FIM tokens (#12988) b5146 Mikko Juola 2025-04-17 01:37:05 -07:00
  • 12b17501e6 opencl: fix incorrect local_size index in profiling log (#12868) b5145 kimminsu 2025-04-17 06:25:57 +09:00
  • 015022bb53 vulkan: enable coopmat2 FA gqa and split_k optimizations more often (#12931) b5144 Jeff Bolz 2025-04-16 13:37:25 -05:00
  • b43d89e311 CANN: Add 310P operator support check (#12962) b5143 Chenguang Li 2025-04-16 16:21:05 +08:00
  • 1d19025909 imatrix : use the function name in more error messages Francis Couture-Harpin 2025-04-15 17:48:06 -04:00
  • 635f945ed1 convert : remove imatrix to gguf python script Francis Couture-Harpin 2025-04-15 17:42:26 -04:00
  • a5165a6ca9 imatrix : two-way conversion between old format and GGUF Francis Couture-Harpin 2025-04-15 17:29:57 -04:00
  • 80f19b4186 opencl: split ggml-opencl.cl into multiple files and cleanup (#12886) b5142 lhez 2025-04-15 12:26:00 -07:00
  • f8f820cc4d metal : add FA-vec kernels for head size 96 (#12952) b5141 Georgi Gerganov 2025-04-15 14:45:05 +03:00
  • 54a7272043 CANN: Add x86 build ci (#12950) b5140 hipudding 2025-04-15 19:08:55 +08:00
  • 84778e9770 CUDA/HIP: Share the same unified memory allocation logic. (#12934) David Huang 2025-04-15 17:20:38 +08:00
  • 510676475f SYCL: Add ROPE vision kernel (#12887) b5138 Akarshan Biswas 2025-04-15 14:07:42 +05:30
  • daa422881a llama : DeepSeek V2/V3 MLA implementation (#12801) b5137 Juk Armstrong 2025-04-15 07:49:57 +01:00
  • eccc7a1602 ggml : Add AVX512 implementation of GEMM - Q4_Kx8 (#12829) b5136 Srihari-mcw 2025-04-15 11:52:36 +05:30
  • 0019279bb5 CANN: Opt ROPE optimization (#12865) b5135 Chenguang Li 2025-04-15 10:09:35 +08:00
  • b0c75ac9f9 CANN: Optimize CANN buffer pool memory management (#12875) b5134 Xinpeng Dou 2025-04-15 10:04:24 +08:00
  • d6d2c2ab8c Add performance print for gemma3 in example (#12929) b5133 Russyyds 2025-04-15 01:18:20 +08:00
  • 75afa0ae31 SYCL: Fix im2col (#12910) b5132 Akarshan Biswas 2025-04-14 17:53:53 +05:30
  • c772d54926 rpc : use ggml_context_ptr (#12938) b5131 Radoslav Gerganov 2025-04-14 13:59:34 +03:00
  • 81c7e64fc2 dsiable curl lib check, this action is missed by commit bd3f59f812 (#12761) (#12937) Neo Zhang Jianyu 2025-04-14 18:19:07 +08:00
  • 526739b879 sync : ggml b5129 Georgi Gerganov 2025-04-14 08:52:10 +03:00
  • a25355e264 cpu: fix cpu backend's supports-op for GET_ROWS_BACK. fixes a fatal when running test-backend-ops with only the CPU backend (ggml/1190) cmdr2 2025-04-11 12:14:19 +05:30
  • e959d32b1c ggml: use _mm[512/256]_dpbusd[_avx]_epi32 to directly accumulate into the result register (#12773) b5127 SXX 2025-04-14 13:47:55 +08:00
  • 307bfa253d ggml: disable CUDA graphs for unsupported DUP and CONT node types (#12891) b5126 Alan Gray 2025-04-13 22:12:21 +01:00
  • 71e90e8813 quantize: Handle user-defined quantization levels for additional tensors (#12511) b5125 Ed Addario 2025-04-13 19:29:28 +01:00
  • 16202d6f96 Merge branch 'master' into compilade/imatrix-batched-chunks Francis Couture-Harpin 2025-04-13 12:10:02 -04:00
  • bc091a4dc5 common : Define cache directory on AIX (#12915) b5124 Prajwal B Mehendarkar 2025-04-12 21:03:39 +05:30
  • a4837577aa vulkan: use aligned loads for flash attention mask (#12853) b5123 Jeff Bolz 2025-04-12 03:44:48 -05:00
  • e59ea539b8 llava: Fix cpu-only clip image encoding sefault (#12907) b5122 Matt Clayton 2025-04-12 01:29:03 -04:00
  • 3fe362fe49 gguf-py : use ThreadPoolExecutor when writing tensors compilade/parallel-convert Francis Couture-Harpin 2025-04-12 00:00:51 -04:00
  • c94085df28 server : add VSCode's Github Copilot Chat support (#12896) b5121 Georgi Gerganov 2025-04-11 23:37:41 +03:00
  • e8a62631b3 rpc : Set cache directory in rpc-server.cpp on FreeBSD (#12903) b5120 yuri@FreeBSD 2025-04-11 13:04:14 -07:00
  • b6930ebc42 tool-call: fix non-tool-calling grammar crashes w/ Qwen / Hermes 2 templates (#12900) b5119 Olivier Chafik 2025-04-11 12:47:52 -07:00
  • 68b08f36d0 common : Define cache directory on FreeBSD (#12892) b5118 yuri@FreeBSD 2025-04-11 12:45:44 -07:00
  • d7db1593ee Merge branch 'master' into compilade/parallel-convert Francis Couture-Harpin 2025-04-11 15:18:33 -04:00
  • 578754b315 sycl: Support sycl_ext_oneapi_limited_graph (#12873) b5117 Ewan Crawford 2025-04-11 15:32:14 +02:00
  • b2034c2b55 contrib: support modelscope community (#12664) b5116 tastelikefeet 2025-04-11 20:01:56 +08:00
  • 06bb53ad9b llama-model : add Glm4Model implementation for GLM-4-0414 (#12867) b5115 Yuxuan Zhang 2025-04-11 18:10:10 +08:00
  • 0c50923944 clip : use smart pointer (⚠️ breaking change) (#12869) b5114 Xuan-Son Nguyen 2025-04-11 12:09:39 +02:00
  • fccf9cae83 SYCL: Add fp16 type support to unary op kernels (#12788) b5113 Akarshan Biswas 2025-04-11 13:33:50 +05:30
  • ec6c09d0fa convert : Llama4 RoPE fix (#12889) Daniel Han 2025-04-11 00:49:09 -07:00
  • 8ac9f5d765 ci : Replace freediskspace to free_disk_space in docker.yml (#12861) R0CKSTAR 2025-04-11 15:26:17 +08:00
  • 12e9158f25 xcf : add check for visionos build version (#12854) Daniel Bevenius 2025-04-11 09:24:34 +02:00
  • 5b1f13cb64 convert : proper tensor name mapping for llama4 (#12870) Xuan-Son Nguyen 2025-04-11 09:23:37 +02:00
  • 8b91d5355a llama : correct rms norm for llama 4 (#12882) b5108 Xuan-Son Nguyen 2025-04-11 08:49:50 +02:00
  • 0fed24c347 ggml: fix compilation error s390x (#12848) b5107 Aaron Teo 2025-04-11 13:20:07 +08:00
  • 47ba87d0a4 sync : ggml b5106 Georgi Gerganov 2025-04-11 00:08:23 +03:00
  • 1d2b613445 tests : fix init order (#0) Georgi Gerganov 2025-04-11 00:04:25 +03:00
  • eb420e1148 sync : ggml Georgi Gerganov 2025-04-10 23:59:16 +03:00
  • cb79c2e7fa ggml: don't include arm_neon.h when using CUDA 12 with ARM Neon (ggml/1187) cmdr2 2025-04-10 17:53:08 +05:30
  • fe92821ea9 ggml : add bilinear upscale support (ggml/1185) Diego Devesa 2025-04-09 12:32:13 +02:00
  • 459895c326 ggml : add more generic custom op, remove deprecated custom ops (ggml/1183) Diego Devesa 2025-04-09 12:31:34 +02:00
  • e4bf72d631 scripts : fix sync-ggml-am.sh Georgi Gerganov 2025-04-10 23:59:01 +03:00
  • 8b9cc7cdd8 llava : introduce libmtmd (#12849) b5099 Xuan-Son Nguyen 2025-04-10 22:57:16 +02:00
  • 64eda5deb9 convert : ability to lazy-load safetensors remotely without downloading to disk (#12820) Xuan-Son Nguyen 2025-04-10 17:24:44 +02:00
  • 098f0e5eea test gg/test-fp16 Georgi Gerganov 2025-04-10 12:35:16 +03:00
  • fe5b78c896 CANN: Support more ops (#12841) b5097 Chenguang Li 2025-04-10 08:51:52 +08:00
  • 11d07e1e69 Fixes #12823 (#12830) b5096 Prajwal B Mehendarkar 2025-04-10 04:48:01 +05:30
  • b0091ecc1e docker : added all CPU to GPU images (#12749) Rudi Servo 2025-04-09 23:17:12 +00:00
  • 31f7803bc4 ggml-cpu-impl.h: do not redefine bool on POWER9 (#12856) b5094 Piotr Kubaj 2025-04-09 23:00:34 +00:00
  • 2391506ace ggml-impl.h: fix build on POWER9 (#12855) b5093 Piotr Kubaj 2025-04-09 23:00:25 +00:00
  • d3bd7193ba llama : Support Qwen3 and Qwen3MoE (#12828) b5092 Bo Zheng 2025-04-09 17:47:36 +08:00
  • d9a63b2f2e musa: enable freediskspace for docker image build (#12839) R0CKSTAR 2025-04-09 17:22:30 +08:00
  • 8ed71242f4 sycl: update documentation to use -no-cnv (#12845) Romain Biessy 2025-04-09 11:22:04 +02:00
  • 381603a775 ci: detach common from the library (#12827) b5089 Plamen Minev 2025-04-09 11:11:11 +03:00
  • 65a69e6e1b clip : do not print ftype (#12832) Xuan-Son Nguyen 2025-04-09 10:09:53 +02:00
  • 47277d6d1d readme : add rpc backend (#12842) Georgi Gerganov 2025-04-09 10:54:42 +03:00
  • 6e1c4cebdb CANN: Support Opt CONV_TRANSPOSE_1D and ELU (#12786) b5086 Chenguang Li 2025-04-09 14:04:14 +08:00
  • 0090950f67 vulkan: In coopmat2 mmq, load q4_k/q5_k scales through shared memory (#12833) b5085 Jeff Bolz 2025-04-09 00:25:08 -05:00
  • 7ecd780b1a vulkan: Use fp16 for the flash attention P*V multiplication (#12783) b5084 Jeff Bolz 2025-04-09 00:12:57 -05:00
  • d8bab9efa1 gguf-py : add more clarifying comments for multi-thread writes Francis Couture-Harpin 2025-04-08 21:55:15 -04:00