upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-26 12:40:58 -05:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 42fc243060 opencl: fix fused RMS norm mul view offset (#26085) master yzyyzyhhh 2026-07-26 23:01:08 +08:00
  • ff067f76dd ui: fix context gauge card regressions and land at the conversation end (#26099) b10133 Pascal 2026-07-26 06:51:10 +02:00
  • 7cdd557f76 ggml-webgpu: Fix WASM compilation with OpenMP (#25943) Reese Levine 2026-07-25 17:37:18 -07:00
  • 474aef9770 migrate server-mcp xsn/common_subproc Xuan Son Nguyen 2026-07-26 01:11:28 +02:00
  • 8bb909374d common : use-after-free when loading LoRA adapter fails (#25611) Nicky Mouha 2026-07-25 19:10:32 -04:00
  • a3d10e33f9 Merge branch 'master' into xsn/common_subproc Xuan Son Nguyen 2026-07-26 01:09:25 +02:00
  • 20455a4ad3 server: support MCP stdio (#26062) Xuan-Son Nguyen 2026-07-26 01:08:49 +02:00
  • 355303edab hexagon: partial im2col support (#26007) Todor Boinovski 2026-07-25 15:47:29 -07:00
  • c812c543f8 common : skip empty implicit default preset (#25643) hogeheer499-commits 2026-07-25 21:15:27 +02:00
  • abc348790e server: add format arg to datetime tool (#26117) Xuan-Son Nguyen 2026-07-25 21:15:15 +02:00
  • 2cfc7670ed server : add missing task parameters(adaptive_target, adaptive_decay) in generation_settings (#25830) Tekin Ertekin 2026-07-25 21:53:08 +03:00
  • d8efdcbdb8 server: add format arg to datetime tool xsn/tool_datetime_format Xuan Son Nguyen 2026-07-25 18:23:28 +02:00
  • 720d7fa409 vendor : update cpp-httplib to 0.51.0 (#26067) Adrien Gallouët 2026-07-25 18:16:29 +02:00
  • 33f3ec1b67 server: make MCP test fixtures JSON-RPC 2.0 compliant xsn/server_mcp_stdio Pascal 2026-07-25 17:40:53 +02:00
  • 08a384bd77 server: fix MCP zombie leak and timeout-induced transport teardown Pascal 2026-07-25 17:28:59 +02:00
  • fb92d8f187 Update ggml/src/gguf.cpp : Defined virtual keyword for destructor of gguf_writer_base (#25867) Yongmin Yoo 유용민 2026-07-25 21:32:37 +09:00
  • 910196f6b3 common : add support for multiple end sequences in the reasoning budget sampler (#25544) Aldehir Rojas 2026-07-25 04:58:09 -05:00
  • a99b462daa fix response schema + docs Xuan Son Nguyen 2026-07-25 11:28:30 +02:00
  • 07d65d6227 fix last_error data race Xuan Son Nguyen 2026-07-25 11:25:49 +02:00
  • d67c0b4107 tests: synchronize save-load-state generation (#26056) helanfxz 2026-07-25 16:23:31 +08:00
  • cbf34687d0 fix missing Q2_0 type in cm2 matmul 0cc4m/vulkan-mul-mm-refactor Ruben Ortlam 2026-07-25 09:54:34 +02:00
  • 0308ae8cce fix order of load modes 0cc4m/mmap-auto Ruben Ortlam 2026-07-25 09:36:56 +02:00
  • 20cc96ff43 make is_created atomic Xuan Son Nguyen 2026-07-25 02:13:07 +02:00
  • a1de37181e disable subproc on wasm Xuan Son Nguyen 2026-07-25 02:05:18 +02:00
  • 600bb60808 mtmd: disable video if subproc is not set Xuan Son Nguyen 2026-07-25 02:05:12 +02:00
  • e6d477bcae test-jinja: use common subproc Xuan Son Nguyen 2026-07-25 02:04:56 +02:00
  • c063f10698 disabled by default on android and ios Xuan Son Nguyen 2026-07-25 01:35:56 +02:00
  • 062bd334a8 add compile flag LLAMA_SUBPROCESS Xuan Son Nguyen 2026-07-25 01:34:13 +02:00
  • 8e000ac754 add common/subproc.h|cpp Xuan Son Nguyen 2026-07-25 01:22:54 +02:00
  • 555881ebc8 ui: reduce per-token render cost when streaming (#26053) b10121 Zach Winter 2026-07-24 16:09:46 -04:00
  • 96013c5112 ui: remove render effects (#26083) Pascal 2026-07-24 21:43:23 +02:00
  • 6dfc0857fc fix some edge cases Xuan Son Nguyen 2026-07-24 21:30:23 +02:00
  • a669ac5a55 Merge branch 'master' into xsn/server_mcp_stdio Xuan Son Nguyen 2026-07-24 21:19:36 +02:00
  • 49d0ad7b98 internal/mcp-stdio: integration + tests + fixes (#26075) Piotr Wilkin (ilintar) 2026-07-24 21:19:09 +02:00
  • 88bfee1429 model: add GLM 5.2 Indexer support (#25407) Pedro Cuenca 2026-07-24 20:55:56 +02:00
  • 95a923a64c ui: fix MCP server display name conflicts in tools lists (#26011) Pascal 2026-07-24 19:28:14 +02:00
  • 27209a598d server: support "reasoning_effort": "none" in OAI API (#26045) Nigel Bosch 2026-07-24 12:19:10 -05:00
  • 298219f985 llama: various bug fixes (#26051) Xuan-Son Nguyen 2026-07-24 18:56:42 +02:00
  • fa72aeccb2 HIP: remove rocWMMA FlashAttention (#26046) Johannes Gäßler 2026-07-24 17:53:54 +02:00
  • 8657691a73 set mmap_support to false on OpenCL backend Ruben Ortlam 2026-07-24 17:42:20 +02:00
  • 687f6191a1 Update ggml/src/ggml-hexagon/ggml-hexagon.cpp Piotr Wilkin (ilintar) 2026-07-24 17:19:59 +02:00
  • ed7adbfefd opencl: cache compiled cl_program binaries on disk (#26050) Hongqiang Wang 2026-07-24 08:14:33 -07:00
  • 56a83860dd opencl: do not treat NULL-mask flash attention as causal (#25771) kumaal 2026-07-24 20:12:01 +05:00
  • 77095ee0cb skill: create add-new-model and code-review (#26042) Xuan-Son Nguyen 2026-07-24 17:04:17 +02:00
  • 5f08fbfcd9 llama: add new default load-mode auto which picks mmap unless a non-Metal iGPU is used Ruben Ortlam 2026-07-24 15:32:38 +02:00
  • 54ce507b6f UI: Fix settings precedence, Factory < Admin (--ui-config-file) < Users (Settings panel) (#26002) Pascal 2026-07-24 15:09:55 +02:00
  • 8f5ab832ca cohere2 moe template parser: enforce JSON schema for text responses if a response schema is provided (#26018) Matt Thompson 2026-07-24 03:54:47 -07:00
  • df6daabc67 Add tensor name to JSON output cross-profiler Piotr Wilkin 2026-06-06 22:33:01 +02:00
  • 9ed6048dd9 tentative Metal support Piotr Wilkin 2026-05-19 11:52:22 +02:00
  • 2ade1b825a Add missing unrolls Piotr Wilkin 2026-05-16 15:47:06 +02:00
  • 695dd1ea54 Revert accidental change. Piotr Wilkin 2026-05-13 17:22:19 +02:00
  • f1c08eac44 Fix braces Piotr Wilkin 2026-05-13 11:09:53 +02:00
  • 4947172470 Fix FATTN profiling Piotr Wilkin 2026-05-12 23:58:28 +02:00
  • c7d42e000a Converge implementation with export-graph-ops Piotr Wilkin 2026-04-07 22:01:00 +02:00
  • bfbf84a467 Add missing op parameters to the profiler; add support for test-backend-ops to run performance tests with exactly the tensor shapes from the run Piotr Wilkin 2026-04-03 17:41:57 +02:00
  • abdf1bf2a6 docs, pass copy details Piotr Wilkin 2026-03-29 23:35:38 +02:00
  • 7c22aecdd9 fix mul_mat_id stats, add throughput stat, add envvar trigger, add concurrent mode fix Piotr Wilkin 2026-03-29 22:52:33 +02:00
  • 2a2476e17a fix builds, integrate vulkan profiler, fix copy events, fix export Piotr Wilkin 2026-03-29 16:52:50 +02:00
  • 609c786703 Fix more missing backend stuff (and Python errors) Piotr Wilkin 2026-03-29 01:57:02 +01:00
  • 153f8d923c add second dimension to reported tensors, fix Mac build, add missing initializer to all backends Piotr Wilkin 2026-03-29 01:49:52 +01:00
  • 7705d453a5 feat: cool profiler thingy Piotr Wilkin 2026-03-29 01:14:09 +01:00
  • 0cea36222f vendor: update subprocess.h (#26061) Xuan-Son Nguyen 2026-07-24 08:02:23 +02:00
  • fd88e926f6 server_mcp_stdio is now framing-only, no json Xuan Son Nguyen 2026-07-24 07:41:38 +02:00
  • fcf91702b2 server_mcp_transport Xuan Son Nguyen 2026-07-24 07:38:40 +02:00
  • 2beaeaa216 stderr drain Xuan Son Nguyen 2026-07-24 07:29:57 +02:00
  • 84f13f901c vendor: update subprocess.h xsn/bump_subproc Xuan Son Nguyen 2026-07-24 07:21:04 +02:00
  • bbf240a113 add server_mcp_stdio Xuan Son Nguyen 2026-07-24 07:21:54 +02:00
  • 7804b57f3e vendor: update subprocess.h Xuan Son Nguyen 2026-07-24 07:21:04 +02:00
  • 40908874f1 init impl Xuan Son Nguyen 2026-07-24 06:56:53 +02:00
  • f5addb42f6 move server_pipe to common Xuan Son Nguyen 2026-07-24 06:18:03 +02:00
  • 0a50d9909a hexagon: further improved pipeline of the core bits (L2, DMA, MM, FA) (#26049) b10108 Max Krasnyansky 2026-07-23 19:13:03 -07:00
  • c867e1c38c llama: various bug fixes xsn/ub_fix_2 Xuan Son Nguyen 2026-07-23 21:03:06 +02:00
  • b60794b60f nits xsn/skill_add_models Xuan Son Nguyen 2026-07-23 18:51:19 +02:00
  • b1f66cb3b8 conversion-time weight modification Xuan Son Nguyen 2026-07-23 18:50:53 +02:00
  • b382579a57 Apply suggestions from code review Xuan-Son Nguyen 2026-07-23 18:45:09 +02:00
  • e80a12fd77 exclude ggml-gh-bot Xuan Son Nguyen 2026-07-23 18:42:16 +02:00
  • c0bc8591e8 hexagon: fix Windows crash when op_poll is enabled (#26029) b10107 adgup-qti 2026-07-23 21:38:10 +05:30
  • f53745b438 add design review Xuan Son Nguyen 2026-07-23 16:20:08 +02:00
  • 184eb2b901 mention about skills in agents.md Xuan Son Nguyen 2026-07-23 16:00:26 +02:00
  • 2fad89caaf add security review section Xuan Son Nguyen 2026-07-23 15:55:42 +02:00
  • 090cecde1d add codeowners Xuan Son Nguyen 2026-07-23 15:23:30 +02:00
  • ce82869361 nits Xuan Son Nguyen 2026-07-23 15:22:43 +02:00
  • 7afa9586ed add code review skill Xuan Son Nguyen 2026-07-23 15:21:51 +02:00
  • 1e760f9946 add common pitfalls Xuan Son Nguyen 2026-07-23 15:10:14 +02:00
  • 6e7be395c1 skill: add new model Xuan Son Nguyen 2026-07-23 14:58:32 +02:00
  • 1425386fd9 CUDA: fix external compilation of q1_0 MMQ (#25778) b10106 Johannes Gäßler 2026-07-23 14:45:51 +02:00
  • e6dd0e29a6 args: refactor mlock/mmap/directio into load-mode (#20834) b10105 Aaron Teo 2026-07-23 20:32:56 +08:00
  • 16a2011d40 ggml: fix backend split scheduler race condition 0cc4m/backend-split-sync-fix Ruben Ortlam 2026-07-23 14:07:43 +02:00
  • ef6de50a47 ggml: fix backend split scheduler race condition 0cc4m/vulkan-sync-fixes Ruben Ortlam 2026-07-23 14:07:43 +02:00
  • 76f9383dc6 vulkan: synchronization fixes Ruben Ortlam 2026-07-22 14:05:53 +02:00
  • da296d6e72 contrib: fix leftovers from the AI usage policy update (#26030) Pascal 2026-07-23 12:32:23 +02:00
  • c588c4f476 metal : add f16 type support to leaky relu (#25981) b10103 Ilia Ilmer 2026-07-22 23:45:46 -04:00
  • d941f6e1c9 conversion: fix non-MoE NomicBert GGUF conversion error (#25996) Shahir BIn Zulfiker 2026-07-23 09:01:35 +06:00
  • 4310aa4f87 contrib: allow all AI-generated code in general (#26012) Xuan-Son Nguyen 2026-07-23 00:29:03 +02:00
  • cf512566dc ui: Add a "Default" option for the reasoning selector (#25846) Pascal 2026-07-22 23:09:49 +02:00
  • 4a94f386b9 contrib: allow all AI-generated code in general xsn/contrib_ai_gen Xuan Son Nguyen 2026-07-22 19:35:20 +02:00
  • 1a064ab092 CUDA: Improve NVFP4 W4A4 activation quantization (#25730) b10099 Oliver Simons 2026-07-22 19:28:02 +02:00
  • 0278d8362d hexagon: activation ops update (#25974) b10098 Todor Boinovski 2026-07-22 09:25:04 -07:00
  • e0833bf686 mtmd: use RAII for setting and resetting non-causal attention (#25723) Niklas Wenzel 2026-07-22 18:10:03 +02:00
  • 61328e6a91 feat(ui): add symbolic math support to JS sandbox via nerdamer (#25948) rankaiyx 2026-07-22 23:52:55 +08:00