wylab/llama.cpp
1
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-16 01:15:58 +02:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • ff90508d68 contributing: update guidelines for AI-generated code (#17625) b7212 Xuan-Son Nguyen 2025-11-30 22:51:34 +01:00
  • 0a4aeb927d cmake : add option to build and link LibreSSL (#17552) b7211 Adrien Gallouët 2025-11-30 22:14:32 +01:00
  • 2ba719519d model: LFM2-VL fixes (#17577) b7210 Tarek Dakhran 2025-11-30 21:57:31 +01:00
  • 7f8ef50cce clip: fix nb calculation for qwen3-vl (#17594) b7209 Xuan-Son Nguyen 2025-11-30 15:33:55 +01:00
  • 3c136b21a3 cli: add migration warning (#17620) b7208 Xuan-Son Nguyen 2025-11-30 15:32:43 +01:00
  • beb1f0c503 common : throttle download progress output to reduce IO flush (#17427) b7207 Adrien Gallouët 2025-11-30 13:22:44 +01:00
  • def5404f26 common: add LLAMA_LOG_FILE env var (#17609) b7206 Aaron Teo 2025-11-30 19:12:32 +08:00
  • 80742cbaeb cont : naming Georgi Gerganov 2025-11-30 00:07:13 +02:00
  • fa0465954f ggml: fix: macOS build with -DGGML_BACKEND_DL=ON (#17581) b7205 Gilad S. 2025-11-30 04:00:59 +02:00
  • 5a6241feb0 common: update env var name (#17588) b7204 ddh0 2025-11-29 19:59:25 -06:00
  • c7af376c29 CUDA: add stream-based concurrency (#16991) b7203 Aman Gupta 2025-11-30 08:17:55 +08:00
  • 00425e2ed1 cuda : add error checking for cudaMemcpyAsync in argsort (#17599) b7202 Mahekk Shaikh 2025-11-29 19:16:28 -05:00
  • 385c3da5e6 vulkan : fix FA mask load with bounds check (coopmat2) (#17606) b7201 Acly 2025-11-30 01:03:21 +01:00
  • c187003d81 llama : naming Georgi Gerganov 2025-11-30 00:05:47 +02:00
  • 1760bd69b3 llama : reserve graphs with samplers Georgi Gerganov 2025-11-29 23:57:25 +02:00
  • 467746e3ad Merge branch 'master' into HEAD Georgi Gerganov 2025-11-29 23:17:25 +02:00
  • ff7b0bf632 llama : call backend_init once Georgi Gerganov 2025-11-29 23:09:53 +02:00
  • ab49f094d2 server: move server-context to its own cpp|h (#17595) b7200 Xuan-Son Nguyen 2025-11-29 22:04:44 +01:00
  • d8d98bb4bb Merge branch 'master' into HEAD Georgi Gerganov 2025-11-29 22:38:44 +02:00
  • 9028ebfea8 llama : cleanup + naming Georgi Gerganov 2025-11-29 22:37:07 +02:00
  • 8c32d9d96d server: explicitly set the function name in lambda (#17538) b7199 Haiyue Wang 2025-11-30 01:43:29 +08:00
  • 0874693b44 common : fix json schema with '\' in literals (#17307) b7198 Igor Smirnov 2025-11-29 21:06:32 +05:00
  • 865bcb4abc release: bugfix missing .tar.gz upload fix-release-duplicate-libs-b7137-865bcb4 Aaron Teo 2025-11-29 23:46:34 +08:00
  • bd119c7471 release: undo debug info and attempt release fix-release-duplicate-libs-b7136-bd119c7 Aaron Teo 2025-11-29 23:04:02 +08:00
  • fbc8f49f3c llama : simplify Georgi Gerganov 2025-11-29 15:58:59 +02:00
  • a00ecf21eb release: debug file info Aaron Teo 2025-11-29 22:50:24 +08:00
  • 7d2add51d8 sycl : support to malloc memory on device more than 4GB, update the doc and script (#17566) b7197 Neo Zhang 2025-11-29 20:59:44 +08:00
  • 76f6335fef release: disable release workflow for debug Aaron Teo 2025-11-29 20:59:41 +08:00
  • f698a79c63 ggml: replace hwcap with riscv_hwprobe for RVV detection (#17567) b7196 ixgbe 2025-11-29 20:56:31 +08:00
  • 751a3cf956 release: update release message Aaron Teo 2025-11-29 19:42:19 +08:00
  • f5335532e5 release: switch to .tar.gz Aaron Teo 2025-11-29 19:02:18 +08:00
  • 47a268ea50 Vulkan: MMVQ Integer Dot K-Quant and MUL_MAT_ID support (#16900) b7195 Ruben Ortlam 2025-11-29 09:37:22 +01:00
  • 59d8d4e963 vulkan: improve topk perf for large k, fix overflow in unit tests (#17582) b7194 Jeff Bolz 2025-11-29 01:39:57 -06:00
  • d82b7a7c1d gguf-py : fix passing non-native endian tensors (editor-gui and new-metadata) (#17553) b7193 Aleksei Nikiforov 2025-11-28 20:53:01 +01:00
  • 03914c7ef8 common : move all common_chat_parse_* to chat-parser.cpp. (#17481) b7192 DAN™ 2025-11-28 13:29:36 -05:00
  • 3ce7a65c2f server: fix: /metrics endpoint returning JSON-escaped Prometheus format (#17386) b7191 o7si 2025-11-29 02:14:00 +08:00
  • e072b2052e ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (#17276) b7190 Diego Devesa 2025-11-28 07:33:23 -08:00
  • 2464d1b3fc sampling : simplify Georgi Gerganov 2025-11-28 17:21:12 +02:00
  • 8cac9dee45 sampling : use logits directly for min-p filtering Daniel Bevenius 2025-11-28 16:12:05 +01:00
  • 333da805fe Add initial version for top-p sampling Oliver Simons 2025-11-28 15:08:20 +01:00
  • 117e2079a9 refactor : simplify and improve memory management Georgi Gerganov 2025-11-28 11:47:59 +02:00
  • c6f7a423c8 [MUSA] enable fp16/fast_fp16/bf16_mma on PH1 (#17551) b7189 R0CKSTAR 2025-11-28 21:08:29 +08:00
  • 459b7ae7b9 squash! sampling : support intermixed backend/cpu samplers Daniel Bevenius 2025-11-28 13:46:51 +01:00
  • 2e7ef98f18 ggml-cuda: add stricter checking for fusion (#17568) b7188 Aman Gupta 2025-11-28 20:34:51 +08:00
  • ddf9f94389 server : add Anthropic Messages API support (#17570) b7187 Fredrik Hultin 2025-11-28 12:57:04 +01:00
  • ff55414c42 model : Qwen3 Next (#16095) b7186 Piotr Wilkin (ilintar) 2025-11-28 12:02:56 +01:00
  • 73955f7d2a CUDA: no FP16 arithmetic for vector FA kernel (#17558) b7185 Johannes Gäßler 2025-11-28 10:29:09 +01:00
  • 35cf8887e1 vulkan: Implement GGML_OP_TRI (#17503) b7184 Jeff Bolz 2025-11-28 03:07:29 -06:00
  • 15d2b46b4d rpc : cache and reuse compute graphs (#15405) b7183 Radoslav Gerganov 2025-11-28 10:33:51 +02:00
  • 9ad6522be6 squash! sampling : support intermixed backend/cpu samplers Daniel Bevenius 2025-11-28 08:57:48 +01:00
  • 74be332e24 sampling : support intermixed backend/cpu samplers Daniel Bevenius 2025-11-27 19:39:41 +01:00
  • 6bca76ff5e HIP: enable mul_mat_f for RDNA4 (#17437) b7182 yulo 2025-11-28 15:24:30 +08:00
  • cd0e3a7a3b SOLVE_TRI CUDA kernel for small matrices (#17457) b7181 Piotr Wilkin (ilintar) 2025-11-28 05:15:32 +01:00
  • efaaccdd69 refactor pad_reflect_1d to make the UT case pass (#17204) b7180 Neo Zhang Jianyu 2025-11-28 08:50:56 +08:00
  • f9889cf1c7 Fix top-k comp & behavior for non-CUB path Oliver Simons 2025-11-27 16:40:41 +01:00
  • 4abef75f2c vulkan: Implement SOLVE_TRI (#17486) b7179 Jeff Bolz 2025-11-27 08:48:00 -06:00
  • c386114922 arch : add description about LLM_TENSOR_INFOS (#17550) b7178 Georgi Gerganov 2025-11-27 16:34:13 +02:00
  • e9d070980b sampling : remove backend sampling chain from common_sampler Daniel Bevenius 2025-11-27 15:28:37 +01:00
  • 6783b11fb0 models : fix LFM2 tensors (#17548) b7177 Georgi Gerganov 2025-11-27 16:04:29 +02:00
  • c6bba89ea9 arch : add description about LLM_TENSOR_INFOS gg/arch-add-desc Georgi Gerganov 2025-11-27 16:03:09 +02:00
  • 172208afbf sampling : add comments about backend sampler [no ci] Daniel Bevenius 2025-11-27 14:59:52 +01:00
  • d93ff58322 models : fix LFM2 tensors gg/lfm-fix-tensors Georgi Gerganov 2025-11-27 14:53:24 +02:00
  • 909072abcf cuda : fix UMA detection on discrete GPUs. (#17537) b7176 matt23654 2025-11-27 11:35:35 +00:00
  • cd8370b408 ggml-cpu: aarm64: q4_K repack gemm and gemv implementations (dotprod only) (#17494) b7175 Alberto Cabrera Pérez 2025-11-27 11:25:14 +00:00
  • d21a76ac38 devops: Add build-essential to Ubuntu 26.04 image (#17531) Eric Curtin 2025-11-27 10:35:47 +00:00
  • 4fcd87cf7c gguf-py : skip endian-conversion of MXFP4 data (#17523) Aleksei Nikiforov 2025-11-27 11:35:38 +01:00
  • 5ea3be265b cuda : fix top-k compilation when CUB is unavailable Daniel Bevenius 2025-11-27 09:40:13 +01:00
  • 51107a0b63 sampling : fix temperature check to allow zero temperature Daniel Bevenius 2025-11-27 09:18:43 +01:00
  • d9d736102b sampling : use argmax for min-p sampling Daniel Bevenius 2025-11-27 07:38:44 +01:00
  • b78db3bd50 vulkan : move contiguous checks to device_supports_op (#17490) b7172 Acly 2025-11-27 06:54:19 +01:00
  • 142df17c9c vulkan: use a fixed 1KB buffer for the add_rms_fusion opt (#17514) b7171 Jeff Bolz 2025-11-26 23:32:30 -06:00
  • e509411cf1 server: enable jinja by default, update docs (#17524) b7170 Xuan-Son Nguyen 2025-11-27 01:02:50 +01:00
  • 7cba58bbea opencl: add sqr, sqrt, mean and ssm_conv (#17476) b7169 lhez 2025-11-26 13:29:58 -08:00
  • 5449367b21 Fix chunks being too small with small matrix sizes (#17526) b7168 Alberto Cabrera Pérez 2025-11-26 21:14:54 +00:00
  • 1d594c295c clip: (minicpmv) fix resampler kq_scale (#17516) b7167 Han Qingzhe 2025-11-27 04:44:07 +08:00
  • 7c2bfb352e Merge remote-tracking branch 'upstream/master' into backend-sampling Daniel Bevenius 2025-11-26 17:52:29 +01:00
  • 90a3aff2c2 cuda : fix editorconfig-checker warning Daniel Bevenius 2025-11-26 17:44:04 +01:00
  • eec1e33a9e vulkan: allow graph_optimize for prompt processing workloads (#17475) b7166 Jeff Bolz 2025-11-26 09:46:33 -06:00
  • 879d673759 vulkan: Implement top-k (#17418) b7165 Jeff Bolz 2025-11-26 09:45:43 -06:00
  • 0f7805f32a common : add get_active_samplers function to check enabled samplers Daniel Bevenius 2025-11-26 13:12:36 +01:00
  • 4fea191c66 Use FetchContent over CPM as it's bundled with CMake Oliver Simons 2025-11-26 15:00:24 +01:00
  • 6ab4e50d9c ggml-cpu : add RISC-V Zvfh impl for ggml_vec_mad_f16 (#17448) b7164 xctan 2025-11-26 21:33:05 +08:00
  • 2336cc4784 cmake : use EXCLUDE_FROM_ALL to avoid patch-boringssl.cmake (#17520) b7163 Adrien Gallouët 2025-11-26 14:15:21 +01:00
  • e6923caaec ggml : fix ARM feature verification (#17519) b7162 Adrien Gallouët 2025-11-26 14:14:41 +01:00
  • 3e18dba9fd HIP: Patch failed testcase in WMMA-MMQ kernels for RDNA 4 (#17502) b7161 Jiacheng (Jason) Chen 2025-11-26 05:18:48 -05:00
  • b45d504e70 sampling : add min-p backend sampler Daniel Bevenius 2025-11-26 10:50:58 +01:00
  • eeb5605de2 CANN: Add MROPE and IMROPE support (#17401) b7160 hipudding 2025-11-26 16:44:19 +08:00
  • f3a848a3b1 chore: upgrade cpp-httplib from v0.27.0 to v0.28.0 (#17513) b7159 o7si 2025-11-26 15:21:06 +08:00
  • b3b03a7baf vulkan: Implement GGML_OP_CUMSUM (#17479) b7158 Jeff Bolz 2025-11-26 00:08:10 -06:00
  • 05429433a1 examples: add model-backend-compare tool to compare intermediate device tensors with CPU reference 0cc4m/model-backend-compare 0cc4m 2025-11-25 18:05:56 +01:00
  • f23b306cc5 CUDA: Add top-k implementation Oliver Simons 2025-11-21 12:01:32 +01:00
  • ec047e12ee Merge remote-tracking branch 'upstream/master' into backend-sampling Daniel Bevenius 2025-11-25 15:16:44 +01:00
  • 583cb83416 ggml : add ggml_top_k (#17365) b7157 Georgi Gerganov 2025-11-25 15:31:43 +02:00
  • 05872ac885 convert : fix big-endian conversion (#17431) Aleksei Nikiforov 2025-11-25 14:18:16 +01:00
  • 9e5e09d087 sampling : remove backend-dist option (wip) Daniel Bevenius 2025-11-25 13:45:02 +01:00
  • 55ab25caf5 codeowners : remove slaren (#17492) Diego Devesa 2025-11-25 04:00:23 -08:00
  • 064c90d843 CANN: supports out_prod operator for F32 and F16 (#17406) b7154 TianHao324 2025-11-25 17:39:06 +08:00
  • 53dca56d9b Merge remote-tracking branch 'upstream/master' into gpu-sampling Daniel Bevenius 2025-11-25 08:20:50 +01:00
  • 0f17ccdee7 examples : add info about hybrid sampling in batched [no ci] Daniel Bevenius 2025-11-25 08:12:42 +01:00
  • b1846f1c8e webui: add rehype plugin to restore HTML in Markdown table cells (#17477) Pascal 2025-11-25 08:01:02 +01:00