| 2025-11-20 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2025-11-20 |
YangLe | metal : fix compile on macos 11 (whisper/3533) |
commit | commitdiff | tree |
| 2025-11-20 |
Georgi Gerganov | common : more accurate sampling timing (#17382) |
commit | commitdiff | tree |
| 2025-11-20 |
o7si | convert : fix TypeError when loading base model remotel... |
commit | commitdiff | tree |
| 2025-11-20 |
Piotr Wilkin... | ggml : Fix transposed SOLVE_TRI result (#17323) |
commit | commitdiff | tree |
| 2025-11-20 |
Scott Fudally | DGX Spark: UMA support (#17368) |
commit | commitdiff | tree |
| 2025-11-20 |
Adrien Gallouët | ggml : remove useless and error-prone variadic macros... |
commit | commitdiff | tree |
| 2025-11-20 |
sudhiarm | kleidiai: fix zero-size array declaration (#17240) |
commit | commitdiff | tree |
| 2025-11-20 |
ixgbe | ggml-cpu:add RISC-V RVV (Zvfh) optimization for FP16... |
commit | commitdiff | tree |
| 2025-11-19 |
Giuseppe Scrivano | vulkan: implement ADD1, ARANGE, FILL, SOFTPLUS, STEP... |
commit | commitdiff | tree |
| 2025-11-19 |
Jeff Bolz | vulkan: support larger argsort (#17313) |
commit | commitdiff | tree |
| 2025-11-19 |
Jeff Bolz | vulkan: Add copy_transpose shader (#17371) |
commit | commitdiff | tree |
| 2025-11-19 |
Aleksander... | webui: Add a "Continue" Action for Assistant Message... |
commit | commitdiff | tree |
| 2025-11-19 |
Sigbjørn Skjæret | convert : use self.block_count everywhere instead of... |
commit | commitdiff | tree |
| 2025-11-19 |
Aman Gupta | cuda: fix rope fusion for gemma3 (#17378) |
commit | commitdiff | tree |
| 2025-11-19 |
Piotr Wilkin... | Fix too relaxed check on CUDA "fast copy" (can_be_trans... |
commit | commitdiff | tree |
| 2025-11-19 |
Ruben Ortlam | vulkan: force full subgroups for flash attention to... |
commit | commitdiff | tree |
| 2025-11-19 |
Jeremy Rand | ggml-cpu: Don't pass -mpowerpc64 when -mcpu already... |
commit | commitdiff | tree |
| 2025-11-18 |
Xuan-Son Nguyen | chat: fix int overflow, prevent size calculation in... |
commit | commitdiff | tree |
| 2025-11-18 |
Haiyue Wang | vocab : call reserve() for building plamo-2-translate... |
commit | commitdiff | tree |
| 2025-11-18 |
hksdpc255 | common : Generalized XML-style tool-call parsing with... |
commit | commitdiff | tree |
| 2025-11-18 |
jiahao su | ci : change the openEuler-310p image to fix release... |
commit | commitdiff | tree |
| 2025-11-18 |
Georgi Gerganov | gitignore : be more specific about ignored stuff (... |
commit | commitdiff | tree |
| 2025-11-18 |
Chenguang Li | CANN: fix acl_tensor_ptr usage in ASCEND_310P ROPE... |
commit | commitdiff | tree |
| 2025-11-18 |
o7si | fix: resolve undefined variable 'svr' compilation error... |
commit | commitdiff | tree |
| 2025-11-18 |
jiahao su | CANN: Add openEuler-cann in build and release (#17192) |
commit | commitdiff | tree |
| 2025-11-18 |
Jeff Bolz | vulkan: support noncontig i32 copy (#17328) |
commit | commitdiff | tree |
| 2025-11-17 |
Xuan-Son Nguyen | server: split HTTP into its own interface (#17216) |
commit | commitdiff | tree |
| 2025-11-17 |
Ruben Ortlam | vulkan: add log RTE support to fix Nvidia CI (#17320) |
commit | commitdiff | tree |
| 2025-11-17 |
Adrien Gallouët | cmake : fix ARM feature verification (#17170) |
commit | commitdiff | tree |
| 2025-11-17 |
Adrien Gallouët | ggml : add missing AVX512 feature checks (#17270) |
commit | commitdiff | tree |
| 2025-11-17 |
Georgi Gerganov | metal : support I32 -> I32 copy (#17317) |
commit | commitdiff | tree |
| 2025-11-17 |
Georgi Gerganov | metal : faster argsort (#17315) |
commit | commitdiff | tree |
| 2025-11-17 |
Georgi Gerganov | metal : add cumsum (#17305) |
commit | commitdiff | tree |
| 2025-11-17 |
hipudding | CANN: Use smart pointers to manage ACL objects (#17238) |
commit | commitdiff | tree |
| 2025-11-16 |
Pavels Zaicenkovs | vulkan: add LOG operation support for F32 and F16 ... |
commit | commitdiff | tree |
| 2025-11-16 |
Ruben Ortlam | vulkan: fix MMQ quantize_y condition (#17301) |
commit | commitdiff | tree |
| 2025-11-16 |
Eve | ci : revert #16249 (#17303) |
commit | commitdiff | tree |
| 2025-11-16 |
Georgi Gerganov | metal : remove obosolete asserts (#17295) |
commit | commitdiff | tree |
| 2025-11-16 |
Georgi Gerganov | server : handle context overflow during decode (#17267) |
commit | commitdiff | tree |
| 2025-11-16 |
lhez | opencl: fix rms_norm_mul (#17250) |
commit | commitdiff | tree |
| 2025-11-16 |
shaofeiqi | opencl: add kernel to handle mat mul in attention to... |
commit | commitdiff | tree |
| 2025-11-15 |
shani-f | sycl : unify unary kernels with a generic implementatio... |
commit | commitdiff | tree |
| 2025-11-15 |
Aleksander... | webui: Fix clickability around chat processing statisti... |
commit | commitdiff | tree |
| 2025-11-15 |
Pascal | webui: add OAI-Compat Harmony tool-call streaming visua... |
commit | commitdiff | tree |
| 2025-11-15 |
Sigbjørn Skjæret | convert : remove unnecessary chat template patching... |
commit | commitdiff | tree |
| 2025-11-15 |
Jeff Bolz | vulkan: Fuse mul_mat_id+add_id+mul and mul_mat+add... |
commit | commitdiff | tree |
| 2025-11-15 |
Ruben Ortlam | vulkan: Replace 16-bit unpack8 calls to work around... |
commit | commitdiff | tree |
| 2025-11-15 |
Sigbjørn Skjæret | convert : use all parts in safetensors index (#17286) |
commit | commitdiff | tree |
| 2025-11-15 |
Sigbjørn Skjæret | convert : set expert gating func in base class (#17279) |
commit | commitdiff | tree |
| 2025-11-15 |
Ankur Verma | mtmd-cli: Avoid logging to stdout for model loading... |
commit | commitdiff | tree |
| 2025-11-15 |
Giuseppe Scrivano | vulkan: implement ABS and NEG (#17245) |
commit | commitdiff | tree |
| 2025-11-15 |
Jeff Bolz | vulkan: Use ggml_vk_tensor_subbuffer in mul_mat_vec... |
commit | commitdiff | tree |
| 2025-11-15 |
Jeff Bolz | vulkan: skip all-negative-inf blocks in FA (#17186) |
commit | commitdiff | tree |
| 2025-11-15 |
Jeff Bolz | vulkan: change graph_compute to be async and enable... |
commit | commitdiff | tree |
| 2025-11-14 |
Xuan-Son Nguyen | mtmd: add mtmd_log_set (#17268) |
commit | commitdiff | tree |
| 2025-11-14 |
Bartowski | model : add AfmoeForCausalLM support (#16477) |
commit | commitdiff | tree |
| 2025-11-14 |
Marek Hradil jr. | fix : Dangling pointer for non-empty trigger words... |
commit | commitdiff | tree |
| 2025-11-14 |
Georgi Gerganov | server : fix "can batch with" bug (#17263) |
commit | commitdiff | tree |
| 2025-11-14 |
Georgi Gerganov | metal : support argsort for ne00 > 1024 (#17247) |
commit | commitdiff | tree |
| 2025-11-14 |
Georgi Gerganov | metal : make the FA extra sizes consistent (#17143) |
commit | commitdiff | tree |
| 2025-11-14 |
ixgbe | readme : add RVV,ZVFH,ZFH,ZICBOP support for RISC-V... |
commit | commitdiff | tree |
| 2025-11-14 |
Aleksander... | Better UX for handling multiple attachments in WebUI... |
commit | commitdiff | tree |
| 2025-11-13 |
Alberto Cabrera... | ggml-cpu: handle 3d tensors in repack mat_mul (#17241) |
commit | commitdiff | tree |
| 2025-11-13 |
Xuan-Son Nguyen | server: fixing naming conflict res_error (#17243) |
commit | commitdiff | tree |
| 2025-11-13 |
Piotr Wilkin... | ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM... |
commit | commitdiff | tree |
| 2025-11-13 |
Ruben Ortlam | vulkan: remove shell call from vulkan-shaders-gen tool... |
commit | commitdiff | tree |
| 2025-11-13 |
Diego Devesa | sched : fix reserve ignoring user tensor assignments... |
commit | commitdiff | tree |
| 2025-11-13 |
ixgbe | ggml-cpu : add RISC-V vector intrinsic support for... |
commit | commitdiff | tree |
| 2025-11-13 |
bagheera | metal: accelerated conv2d (#17175) |
commit | commitdiff | tree |
| 2025-11-13 |
Georgi Gerganov | Revert "ggml-cpu: handle 3d tensors in repack mat_mul... |
commit | commitdiff | tree |
| 2025-11-13 |
Diego Devesa | ggml-cpu : use template for argsort (#17222) |
commit | commitdiff | tree |
| 2025-11-13 |
TecJesh | CANN: Add cross_entropy_loss op support (#16886) |
commit | commitdiff | tree |
| 2025-11-13 |
Aman Gupta | CUDA: fuse rope + set_rows (#16884) |
commit | commitdiff | tree |
| 2025-11-13 |
Neo Zhang Jianyu | update SYCL support OPs (#17208) |
commit | commitdiff | tree |
| 2025-11-12 |
o7si | vocab : correct bounds check for UGM XCDA array access... |
commit | commitdiff | tree |
| 2025-11-12 |
Johannes Gäßler | CUDA: static assert to prevent misuse of memcpy_1 ... |
commit | commitdiff | tree |
| 2025-11-12 |
Mike Abbott | docker : preserve .so symlinks for docker container... |
commit | commitdiff | tree |
| 2025-11-12 |
Georgi Gerganov | ggml : use std::sort in ggml_argsort CPU implementation... |
commit | commitdiff | tree |
| 2025-11-12 |
Aleksander... | Update packages + upgrade Storybook to v10 (#17201) |
commit | commitdiff | tree |
| 2025-11-12 |
Xuan-Son Nguyen | server: (refactor) implement generator-based API for... |
commit | commitdiff | tree |
| 2025-11-12 |
Xuan-Son Nguyen | ci: add check vendor job (#17179) |
commit | commitdiff | tree |
| 2025-11-12 |
Xuan-Son Nguyen | server: move res_error/res_ok to static function (... |
commit | commitdiff | tree |
| 2025-11-12 |
Alberto Cabrera... | ggml-cpu: handle 3d tensors in repack mat_mul (#17030) |
commit | commitdiff | tree |
| 2025-11-12 |
Adrien Gallouët | cmake : cleanup (#17199) |
commit | commitdiff | tree |
| 2025-11-12 |
Adrien Gallouët | cmake : move OpenSSL linking to vendor/cpp-httplib... |
commit | commitdiff | tree |
| 2025-11-12 |
TecJesh | CANN: Add L2_NORM op support (#16856) |
commit | commitdiff | tree |
| 2025-11-12 |
Neo Zhang Jianyu | [SYCL]fix ci crash about SSM_CONV (#17169) |
commit | commitdiff | tree |
| 2025-11-12 |
Raul Torres | CANN: GGML_CANN_ACL_GRAPH works only USE_ACL_GRAPH... |
commit | commitdiff | tree |
| 2025-11-11 |
Max Krasnyansky | hexagon: various Op fixes (#17135) |
commit | commitdiff | tree |
| 2025-11-11 |
Eve | disable rms norm mul rope for chips with no fp16 rte... |
commit | commitdiff | tree |
| 2025-11-11 |
sudhiarm | ci: add Arm-hosted Graviton4 runner (#17021) |
commit | commitdiff | tree |
| 2025-11-11 |
Xuan-Son Nguyen | vendor: split httplib to cpp/h files (#17150) |
commit | commitdiff | tree |
| 2025-11-11 |
ixgbe | ggml-cpu : add RISC-V RVV (Zvfh) optimization for FP16... |
commit | commitdiff | tree |
| 2025-11-11 |
duduta | ggml-cpu: templateify ggml_compute_forward_rope_f32... |
commit | commitdiff | tree |
| 2025-11-11 |
Charles Xu | kleidiai: add optimized per-channel kernels for Q8_0... |
commit | commitdiff | tree |
| 2025-11-11 |
Mike Abbott | cmake : add version to all shared object files (#17091) |
commit | commitdiff | tree |
| 2025-11-11 |
Nicolas B.... | Install rpc-server when GGML_RPC is ON. (#17149) |
commit | commitdiff | tree |
| 2025-11-11 |
levkropp | convert : register UMT5Model architecture for T5 conver... |
commit | commitdiff | tree |
| 2025-11-10 |
lhez | opencl: add fastdiv and use it in set_rows, ported... |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / llama.cpp / shortlog