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

  • 3b7946034c add server-queue Xuan Son Nguyen 2025-11-18 14:24:46 +01:00
  • e1a756e934 add server-task, server-common Xuan Son Nguyen 2025-11-18 14:15:14 +01:00
  • 4b52e59903 graph : do not include llama-model.h Georgi Gerganov 2025-11-18 13:53:25 +02:00
  • bc4064cfea CANN: fix acl_tensor_ptr usage in ASCEND_310P ROPE (#17347) Chenguang Li 2025-11-18 16:41:52 +08:00
  • 97cb3fd5ae fix: resolve undefined variable 'svr' compilation error (#17348) o7si 2025-11-18 16:10:47 +08:00
  • ffa277a54c CANN: Add openEuler-cann in build and release (#17192) jiahao su 2025-11-18 16:08:55 +08:00
  • da95bf2a85 vulkan: support noncontig i32 copy (#17328) b7091 Jeff Bolz 2025-11-18 00:41:24 -06:00
  • 71574f9273 sampling : enable all backend sampler tests Daniel Bevenius 2025-11-18 07:31:54 +01:00
  • 0de8878c96 server: split HTTP into its own interface (#17216) b7090 Xuan-Son Nguyen 2025-11-17 22:05:44 +01:00
  • 38e2c1b412 vulkan: add log RTE support to fix Nvidia CI (#17320) b7089 Ruben Ortlam 2025-11-17 21:37:49 +01:00
  • cb44fc84e8 cmake : fix ARM feature verification (#17170) b7088 Adrien Gallouët 2025-11-17 21:37:29 +01:00
  • 0710d5f0f8 ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched Enabled in ggml-ci for testing. slaren 2025-11-14 22:04:41 +01:00
  • 67d3b8e84d ggml : add initial cumsum implementation for CUDA Daniel Bevenius 2025-11-17 16:03:04 +01:00
  • a3eb847d24 webui : add backend sampling options Daniel Bevenius 2025-11-17 15:32:33 +01:00
  • f1f3e68511 server : add backend sampling options/configuration Daniel Bevenius 2025-11-17 15:31:30 +01:00
  • 9fe9a00a8a llama-cli : add backend sampler configuration Daniel Bevenius 2025-11-17 15:30:16 +01:00
  • 7884b0e0ac sampling : add support for backend sampling Daniel Bevenius 2025-11-17 15:19:34 +01:00
  • cb623de3fc ggml : add missing AVX512 feature checks (#17270) b7087 Adrien Gallouët 2025-11-17 12:12:00 +01:00
  • 7aaeedc098 metal : support I32 -> I32 copy (#17317) b7086 Georgi Gerganov 2025-11-17 11:52:00 +02:00
  • 3347e6d904 metal : faster argsort (#17315) b7085 Georgi Gerganov 2025-11-17 11:51:48 +02:00
  • 1a139644a8 metal : add cumsum (#17305) b7084 Georgi Gerganov 2025-11-17 11:51:13 +02:00
  • 2376b7758c CANN: Use smart pointers to manage ACL objects (#17238) b7083 hipudding 2025-11-17 08:43:59 +08:00
  • dbed61294a vulkan: add LOG operation support for F32 and F16 (#17183) b7082 Pavels Zaicenkovs 2025-11-16 22:50:09 +01:00
  • dba1cbceb3 tune for RDNA3 0cc4m/vulkan-mmq-bk-step-tuning 0cc4m 2025-11-16 20:21:22 +01:00
  • 94e2c4d2b3 fix warptile 0cc4m 2025-11-16 20:06:04 +01:00
  • 80deff3648 vulkan: fix MMQ quantize_y condition (#17301) b7081 Ruben Ortlam 2025-11-16 19:38:17 +01:00
  • c19b3c378c device tuning 0cc4m 2025-11-16 18:37:04 +00:00
  • 8b1c339bd2 ci : revert #16249 (#17303) Eve 2025-11-16 18:09:17 +00:00
  • 7e8eb9ba0a vulkan: allow MMQ bk_step tuning 0cc4m 2025-11-16 14:25:24 +01:00
  • 6c262ac39c release: fix duplicate libs, store symbolic links Aaron Teo 2025-11-16 19:51:53 +08:00
  • 416e7c7f47 metal : remove obosolete asserts (#17295) b7079 Georgi Gerganov 2025-11-16 09:50:26 +02:00
  • 5b2093becc server : handle context overflow during decode (#17267) b7078 Georgi Gerganov 2025-11-16 09:23:37 +02:00
  • 52e5d421f1 opencl: fix rms_norm_mul (#17250) b7077 lhez 2025-11-15 17:40:14 -08:00
  • 4db5641210 opencl: add kernel to handle mat mul in attention to improve encoding speed (#17181) b7076 shaofeiqi 2025-11-15 17:33:10 -08:00
  • 72bd7321a7 sycl : unify unary kernels with a generic implementation and enable wide operator support (#17213) b7075 shani-f 2025-11-16 01:52:42 +02:00
  • 22e1ce2f81 webui: Fix clickability around chat processing statistics UI (#17278) Aleksander Grygier 2025-11-15 22:41:41 +01:00
  • 1411d9275a webui: add OAI-Compat Harmony tool-call streaming visualization and persistence in chat UI (#16618) Pascal 2025-11-15 21:09:32 +01:00
  • 662192e1dc convert : remove unnecessary chat template patching (#17289) Sigbjørn Skjæret 2025-11-15 20:58:59 +01:00
  • 24dc769f1b vulkan: Fuse mul_mat_id+add_id+mul and mul_mat+add+add. (#17287) b7071 Jeff Bolz 2025-11-15 12:54:23 -06:00
  • 4dca015b7e vulkan: Replace 16-bit unpack8 calls to work around legacy Windows AMD driver bug (#17285) b7070 Ruben Ortlam 2025-11-15 15:18:58 +01:00
  • 9a8860cf5d convert : use all parts in safetensors index (#17286) Sigbjørn Skjæret 2025-11-15 14:12:39 +01:00
  • 9d3ef4809f convert : set expert gating func in base class (#17279) Sigbjørn Skjæret 2025-11-15 14:06:24 +01:00
  • c7b7db0445 mtmd-cli: Avoid logging to stdout for model loading messages in mtmd-cli (#17277) b7067 Ankur Verma 2025-11-15 03:41:16 -08:00
  • 1568d13c2c vulkan: implement ABS and NEG (#17245) b7066 Giuseppe Scrivano 2025-11-15 12:00:29 +01:00
  • 439342ea0b vulkan: Use ggml_vk_tensor_subbuffer in mul_mat_vec(id) paths (#17244) b7065 Jeff Bolz 2025-11-15 04:56:15 -06:00
  • 234ae7d7bd vulkan: skip all-negative-inf blocks in FA (#17186) b7064 Jeff Bolz 2025-11-15 03:37:25 -06:00
  • 38eaf32af1 vulkan: change graph_compute to be async and enable get_tensor_async (#17158) b7063 Jeff Bolz 2025-11-15 02:06:41 -06:00
  • 9b17d74ab7 mtmd: add mtmd_log_set (#17268) b7062 Xuan-Son Nguyen 2025-11-14 15:56:19 +01:00
  • e1fcf8b09b model : add AfmoeForCausalLM support (#16477) b7061 Bartowski 2025-11-14 07:54:10 -05:00
  • 6cd0cf72ce fix : Dangling pointer for non-empty trigger words in lazy grammar construction (#17048) b7060 Marek Hradil jr. 2025-11-14 13:35:26 +01:00
  • d396b43748 server : fix "can batch with" bug (#17263) b7059 Georgi Gerganov 2025-11-14 14:03:45 +02:00
  • 45c6ef7307 metal : support argsort for ne00 > 1024 (#17247) b7058 Georgi Gerganov 2025-11-14 09:36:06 +02:00
  • 2606b0adab metal : make the FA extra sizes consistent (#17143) b7057 Georgi Gerganov 2025-11-14 09:13:34 +02:00
  • 307772fcda readme : add RVV,ZVFH,ZFH,ZICBOP support for RISC-V (#17259) ixgbe 2025-11-14 15:12:56 +08:00
  • f1bad23f88 Better UX for handling multiple attachments in WebUI (#17246) b7055 Aleksander Grygier 2025-11-14 01:19:08 +01:00
  • becc4816dd ggml-cpu: handle 3d tensors in repack mat_mul (#17241) b7054 Alberto Cabrera Pérez 2025-11-13 20:53:00 +00:00
  • c4abcb2457 server: fixing naming conflict res_error (#17243) b7053 Xuan-Son Nguyen 2025-11-13 20:53:47 +01:00
  • 389ac78b26 ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (#17063) b7052 Piotr Wilkin (ilintar) 2025-11-13 19:54:47 +01:00
  • a19bd6f7ce vulkan: remove shell call from vulkan-shaders-gen tool, revert file check (#17219) b7051 Ruben Ortlam 2025-11-13 14:51:21 +01:00
  • dd091e52f8 sched : fix reserve ignoring user tensor assignments (#17232) b7050 Diego Devesa 2025-11-13 04:14:02 -08:00
  • 1215dde7b0 ggml-cpu : add RISC-V vector intrinsic support for silu and cvar operations (#17227) b7049 ixgbe 2025-11-13 20:13:32 +08:00
  • 0cfb19166b metal: accelerated conv2d (#17175) b7048 bagheera 2025-11-13 05:32:44 -06:00
  • 2776db6c81 Revert "ggml-cpu: handle 3d tensors in repack mat_mul (#17030)" (#17233) b7047 Georgi Gerganov 2025-11-13 12:59:37 +02:00
  • 879dec341a ggml-cpu : use template for argsort (#17222) b7046 Diego Devesa 2025-11-13 00:59:05 -08:00
  • 97d5117217 CANN: Add cross_entropy_loss op support (#16886) b7045 TecJesh 2025-11-13 09:39:51 +08:00
  • a90eb94ca9 CUDA: fuse rope + set_rows (#16884) b7044 Aman Gupta 2025-11-13 08:50:01 +08:00
  • 07751f8d44 update SYCL support OPs (#17208) Neo Zhang Jianyu 2025-11-13 08:42:23 +08:00
  • ffb6f3d921 vocab : correct bounds check for UGM XCDA array access (#17215) b7042 o7si 2025-11-13 06:41:02 +08:00
  • 5d6838b74f CUDA: static assert to prevent misuse of memcpy_1 (#17198) b7041 Johannes Gäßler 2025-11-12 23:13:55 +01:00
  • 92bb442ad9 docker : preserve .so symlinks for docker container builds (#17214) Mike Abbott 2025-11-12 12:33:55 -07:00
  • 374fe09cdd ggml : use std::sort in ggml_argsort CPU implementation (#17211) b7039 Georgi Gerganov 2025-11-12 20:43:38 +02:00
  • 8e878f0cb4 Update packages + upgrade Storybook to v10 (#17201) Aleksander Grygier 2025-11-12 19:01:48 +01:00
  • 00c94083b3 server: (refactor) implement generator-based API for task results (#17174) b7037 Xuan-Son Nguyen 2025-11-12 18:50:52 +01:00
  • 017eceed61 ci: add check vendor job (#17179) Xuan-Son Nguyen 2025-11-12 14:56:02 +01:00
  • ee8dd5c658 server: move res_error/res_ok to static function (#17167) b7035 Xuan-Son Nguyen 2025-11-12 14:17:24 +01:00
  • 1c398dc9ec ggml-cpu: handle 3d tensors in repack mat_mul (#17030) b7034 Alberto Cabrera Pérez 2025-11-12 12:52:19 +00:00
  • 52cf111b31 cmake : cleanup (#17199) b7033 Adrien Gallouët 2025-11-12 13:48:30 +01:00
  • 78010a0d52 cmake : move OpenSSL linking to vendor/cpp-httplib (#17177) b7032 Adrien Gallouët 2025-11-12 12:32:50 +01:00
  • 655cddd174 CANN: Add L2_NORM op support (#16856) b7031 TecJesh 2025-11-12 15:11:42 +08:00
  • 5da7664960 [SYCL]fix ci crash about SSM_CONV (#17169) b7030 Neo Zhang Jianyu 2025-11-12 14:44:29 +08:00
  • 23a46ce972 CANN: GGML_CANN_ACL_GRAPH works only USE_ACL_GRAPH enabled (#16861) Raul Torres 2025-11-12 06:37:52 +00:00
  • c273d75375 hexagon: various Op fixes (#17135) b7028 Max Krasnyansky 2025-11-11 15:25:04 -08:00
  • 7d019cff74 disable rms norm mul rope for chips with no fp16 rte (#17134) b7027 Eve 2025-11-11 18:53:30 +00:00
  • 3fe36c3238 ci: add Arm-hosted Graviton4 runner (#17021) sudhiarm 2025-11-11 15:58:05 +00:00
  • 1d45b4228f vendor: split httplib to cpp/h files (#17150) b7025 Xuan-Son Nguyen 2025-11-11 13:32:58 +01:00
  • ca4844062b ggml-cpu : add RISC-V RVV (Zvfh) optimization for FP16 to FP32 conversion (#17161) b7024 ixgbe 2025-11-11 19:41:51 +08:00
  • 73460f6278 ggml-cpu: templateify ggml_compute_forward_rope_f32 and _f16 (#16805) b7023 duduta 2025-11-11 13:33:24 +02:00
  • 8c583242ad kleidiai: add optimized per-channel kernels for Q8_0 (#16993) b7022 Charles Xu 2025-11-11 12:20:31 +01:00
  • 4a5b8aff40 cmake : add version to all shared object files (#17091) b7021 Mike Abbott 2025-11-11 04:19:50 -07:00
  • d2d626938a Install rpc-server when GGML_RPC is ON. (#17149) b7020 Nicolas B. Pierron 2025-11-11 11:53:59 +01:00
  • 2fc392ce35 convert : register UMT5Model architecture for T5 conversion (#17160) levkropp 2025-11-11 03:38:30 -05:00
  • ece0f5c177 opencl: add fastdiv and use it in set_rows, ported from cuda (#17090) b7018 lhez 2025-11-10 15:00:13 -08:00
  • 7bef684118 models : move build_inp_out_ids outside loop (#17151) b7017 Sigbjørn Skjæret 2025-11-10 22:55:30 +01:00
  • 395e286bc9 cpu: skip NOPs to avoid barriers (#17133) b7016 Max Krasnyansky 2025-11-10 12:44:49 -08:00
  • 13730c183b metal : cap threadgroups size of set_rows (#17146) b7015 Georgi Gerganov 2025-11-10 21:33:35 +02:00
  • 967eb4b2bf ggml-cpu : inspect -march and -mcpu to found the CPU (#16333) b7014 Adrien Gallouët 2025-11-10 20:03:36 +01:00
  • f117be185e vulkan: check glslc executable string (#17144) b7013 Ruben Ortlam 2025-11-10 16:59:26 +01:00
  • 85234a4b3a vulkan: fix validation issue introduced by #16868 (#17145) b7012 Ruben Ortlam 2025-11-10 16:59:10 +01:00
  • 0c74f32632 memory: Hybrid context shift (#17009) b7011 Gabe Goodhart 2025-11-10 08:14:23 -07:00
  • e6dbc81569 metal : cap threadgroups size of set_rows gg/metal-set-rows-threads Georgi Gerganov 2025-11-10 16:17:09 +02:00