ggml-org/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-04-05 08:45:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • c08d28d088 ci: lower cuda12 floor to 12.8.1 for broader host compatibility (#21438) master b8667 M1DNYT3 2026-04-05 04:04:00 +03:00
  • 661e9acb36 ci: fix vulkan workflow referencing non-existent action (#21442) Nicholas Sparks 2026-04-04 20:59:51 -04:00
  • b8635075ff common : add gemma 4 specialized parser (#21418) b8665 Aldehir Rojas 2026-04-04 13:39:00 -05:00
  • 9c699074c9 server: Fix undefined timing measurement errors in server context (#21201) b8664 Dan Hoffman 2026-04-04 07:11:19 -07:00
  • d01f6274c0 common : respect specified tag, only fallback when tag is empty (#21413) b8663 Adrien Gallouët 2026-04-04 15:08:03 +02:00
  • 650bf14eb9 llama-model: read final_logit_softcapping for Gemma 4 (#21390) b8662 SamareshSingh 2026-04-04 06:05:10 -05:00
  • b7ad48ebda llama: add custom newline split for Gemma 4 (#21406) b8661 Aman Gupta 2026-04-04 15:06:34 +08:00
  • d006858316 ggml-webgpu: move from parameter buffer pool to single buffer with offsets (#21278) b8660 Reese Levine 2026-04-03 11:40:14 -07:00
  • e439700992 ci: Add Windows Vulkan backend testing on Intel (#21292) Masato Nakasaka 2026-04-04 02:16:44 +09:00
  • 50e0ad08fb server: save and clear idle slots on new task (--clear-idle) (#20993) b8658 Yes You Can Have Your Own 2026-04-03 20:02:27 +03:00
  • f1f793ad06 common/parser: fix call ID detection (Mistral parser mostly) + atomicity for tag-json parsers (#21230) b8657 Piotr Wilkin (ilintar) 2026-04-03 17:51:52 +02:00
  • af5c13841f common : fix tool call type detection for nullable and enum schemas (#21327) b8656 Samanvya Tripathi 2026-04-03 11:51:23 -04:00
  • d35b766819 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 cross-profiler Piotr Wilkin 2026-04-03 17:41:57 +02:00
  • 4cd2db730a docs, pass copy details Piotr Wilkin 2026-03-29 23:35:38 +02:00
  • 7ed999669f 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
  • 31cb80be29 fix builds, integrate vulkan profiler, fix copy events, fix export Piotr Wilkin 2026-03-29 16:52:50 +02:00
  • 5ba2845db3 Fix more missing backend stuff (and Python errors) Piotr Wilkin 2026-03-29 01:57:02 +01:00
  • b8df796af2 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
  • 4310843681 feat: cool profiler thingy Piotr Wilkin 2026-03-29 01:14:09 +01:00
  • 277ff5fff7 docker : bump cuda12 to 12.9.1 (#20920) M1DNYT3 2026-04-03 16:06:45 +03:00
  • 384c0076bc docs: Update build.md: HSA_OVERRIDE_GFX_VERSION clarification (#21331) jeromew 2026-04-03 15:05:14 +02:00
  • 1f34806c44 jinja: coerce input for string-specific filters (#21370) b8653 Sigbjørn Skjæret 2026-04-03 15:03:33 +02:00
  • 887535c33f ci: add more binary checks (#21349) Aaron Teo 2026-04-03 20:50:00 +08:00
  • d3416a4aa9 fix: remove stale assert (#21369) b8651 Piotr Wilkin (ilintar) 2026-04-03 13:40:41 +02:00
  • 77dd86c1f0 cont : re-enable vulkan check gg/ggml-deprecate-add1 Georgi Gerganov 2026-04-03 13:10:10 +03:00
  • 5024efda83 cont : remove tests Georgi Gerganov 2026-04-03 12:55:37 +03:00
  • 20e60f6629 ggml : deprecate GGML_OP_ADD1 Georgi Gerganov 2026-04-03 12:38:13 +03:00
  • 43a4ee4a2c HIP: build eatch ci build test for a different architecture (#21337) uvos 2026-04-03 11:38:22 +02:00
  • f851fa5ab0 fix: add openssl to nix dependencies (#21353) (#21355) Tillerino 2026-04-03 11:21:07 +02:00
  • f1ac84119c ggml-zendnn : add MUL_MAT_ID op support for MoE models (#21315) b8648 Vishal Singh 2026-04-03 14:49:08 +05:30
  • b069b10ab4 vocab: fix Gemma4 tokenizer (#21343) Piotr Wilkin (ilintar) 2026-04-03 10:33:03 +02:00
  • 1d4a5f9380 fix model count exceeded check 0cc4m/server-memory-limit Ruben Ortlam 2026-04-02 11:39:36 +02:00
  • 7666cacf28 move llama_context_device_memory function to llama-ext.h Ruben Ortlam 2026-04-02 11:39:07 +02:00
  • 7e10ec8ff2 add server memory debug logging Ruben Ortlam 2026-04-02 10:07:04 +02:00
  • 4af1a283a6 use memory margin instead of total size limit, apply to each device separately Ruben Ortlam 2026-04-02 09:24:53 +02:00
  • d2892543f4 only set model memory_mb if not previously calculated Ruben Ortlam 2026-03-31 17:37:16 +02:00
  • 24f461b66d use no_alloc to get memory requirements for model load Ruben Ortlam 2026-03-31 16:18:03 +02:00
  • c2df1ac64a estimate with to-be-loaded model size included Ruben Ortlam 2026-03-29 12:18:51 +02:00
  • 8482ffc387 server: add --models-memory-max parameter to allow dynamically unloading models when they exceed a memory size threshold Ruben Ortlam 2026-03-29 10:00:49 +02:00
  • 0c58ba3365 rpc : reuse compute graph buffers (#21299) b8646 Radoslav Gerganov 2026-04-03 10:28:09 +03:00
  • 57ace0d612 chat : avoid including json in chat.h (#21306) b8645 Georgi Gerganov 2026-04-03 09:07:59 +03:00
  • 39b27f0da0 (revert) kv-cache : do not quantize SWA KV cache (#21332) b8644 Georgi Gerganov 2026-04-03 09:07:01 +03:00
  • f49e917876 ci : add AMD ZenDNN label to PR labeler (#21345) b8643 Vishal Singh 2026-04-03 08:05:15 +05:30
  • 7c7d6ce5c7 [HIP] Bump ROCm version to 7.2.1 (#21066) b8642 Slobodan Josic 2026-04-03 00:59:20 +02:00
  • 5208e2d5ba fix: gemma 4 template (#21326) b8641 Piotr Wilkin (ilintar) 2026-04-02 23:31:02 +02:00
  • 7992aa7c8e tests : add unit test coverage for llama_tensor_get_type (#20112) b8640 Bartowski 2026-04-02 16:53:58 -04:00
  • a1cfb64530 ggml-webgpu: add vectorized flash attention (#20709) b8639 Zheyuan Chen 2026-04-02 10:40:42 -07:00
  • 5803c8d115 tests: allow exporting graph ops from HF file without downloading weights (#21182) b8638 Ruben Ortlam 2026-04-02 18:19:20 +02:00
  • 63f8fe0ef4 model, mtmd: fix gguf conversion for audio/vision mmproj (#21309) b8637 Xuan-Son Nguyen 2026-04-02 17:10:32 +02:00
  • 223373742b common : add commentary rules for gpt-oss-20b (#21286) Aldehir Rojas 2026-04-02 08:59:59 -05:00
  • e15efe007d Relax prefill parser to allow space. (#21240) b8635 Piotr Wilkin (ilintar) 2026-04-02 11:29:11 +02:00
  • 6137c325a1 chat : add Granite 4.0 chat template with correct tool_call role mapping (#20804) b8634 Jesus Talavera 2026-04-02 11:28:56 +02:00
  • 17193cce34 kv-cache : do not quantize SWA KV cache (#21277) Georgi Gerganov 2026-04-02 11:54:05 +03:00
  • d6dac92bfd Ignore Transfer-Encoding header. (#20269) Roger Chen 2026-04-02 16:41:19 +08:00
  • dae2bf41c9 sync : ggml b8631 Georgi Gerganov 2026-04-02 10:38:24 +03:00
  • bc07d55922 ggml : bump version to 0.9.11 (ggml/1456) Georgi Gerganov 2026-04-02 10:37:26 +03:00
  • 4888137b17 sycl : fix llama_kv_cache hang when kv_cache is huge: 5GB (#21283) b8629 Neo Zhang 2026-04-02 15:08:32 +08:00
  • fbd441c379 hexagon : add cumsum op support (#21246) b8628 Todor Boinovski 2026-04-01 17:44:02 -07:00
  • c30e012253 contrib : rewrite AGENTS.md, make it more clear about project values (#21270) copilot/compare-kv-shifting-implementation Xuan-Son Nguyen 2026-04-01 23:31:51 +02:00
  • 95a6ebabb2 opencl: fix leak in Adreno q8_0 path (#21212) b8626 lhez 2026-04-01 12:54:58 -07:00
  • 12dbf1da95 server: Bypass API Key validation for WebUI static bundle assets (#21269) b8625 Aleksander Grygier 2026-04-01 21:32:15 +02:00
  • 86221cf6da CUDA: fix FA kernel selection logic (#21271) b8624 Johannes Gäßler 2026-04-01 21:28:19 +02:00
  • 6de97b9d3e kleidiai: add CPU feature detection to CI run script (#20394) Martin Klacer 2026-04-01 18:02:41 +01:00
  • 5a0ed5150a Update Dawn version in WebGPU CI (#20784) Nikhil Jain 2026-04-01 09:53:05 -07:00
  • 8710e5f9b9 hexagon: improve RMS_NORM and DIV accuracy (#21251) Aparna M P 2026-04-01 21:13:08 +05:30
  • 1d6d4cf7a5 fix: tool call parsing for LFM2 and LFM2.5 models (#21242) Jonathan 2026-04-01 07:22:44 -07:00
  • 744c0c7310 llama : rotate activations for better quantization (#21038) Georgi Gerganov 2026-04-01 16:58:01 +03:00
  • 0356e33aaf scripts: add function call test script (#21234) Xuan-Son Nguyen 2026-04-01 15:31:58 +02:00
  • 6422036fcb sync : ggml Georgi Gerganov 2026-04-01 16:02:34 +03:00
  • 296bc0538b ggml : bump version to 0.9.10 (ggml/1454) Georgi Gerganov 2026-04-01 16:01:45 +03:00
  • 6b949d1078 sycl : support nvfp4 type in mul_mat (#21227) Neo Zhang 2026-04-01 18:54:15 +08:00
  • 84f82e846c ggml-cuda: Add generic NVFP4 MMQ kernel (#21074) Michael Wand 2026-04-01 03:04:58 -07:00
  • e1cb817483 memory: respect unified KV cache in hybrid memory for eval tasks (#21224) Ettore Di Giacinto 2026-04-01 11:50:17 +02:00
  • 88d5f8ffc3 CUDA/HIP: Fix kernel slection for mmvq mmid kernel to align host selection with device launch bounds (#21238) uvos 2026-04-01 10:21:20 +02:00
  • d43375ff7f ggml : fix RWKV ops thread assignment (#21226) b8611 Georgi Gerganov 2026-04-01 11:10:25 +03:00
  • 2b86e5cae6 ggml-cpu: fix fallback for RVV kernels without zvfh (#21157) b8610 Taimur Ahmad 2026-04-01 13:10:03 +05:00
  • 88458164c7 CUDA: Add Flash Attention Support for Head Dimension 512 (#20998) b8609 Anav Prasad 2026-04-01 07:07:24 +00:00
  • 4951250235 llama : refactor llama_model_quantize_params to expose a pure C interface (#20346) b8608 Ed Addario 2026-04-01 06:43:00 +01:00
  • 82764c341a ggml webgpu: quantized buffers to u32 + wider browser/device support (#21046) b8607 Reese Levine 2026-03-31 22:38:24 -07:00
  • 825eb91a66 ggml-webgpu: port all AOT operators to JIT (#20728) b8606 Abhijit Ramesh 2026-03-31 15:38:16 -07:00
  • 0fcb3760b2 fix: Use lower-case proxy headers naming (#21235) b8605 Aleksander Grygier 2026-03-31 17:47:46 +02:00
  • 6307ec07d3 common : cleanup logs and modernize the progress bar (#21215) b8604 Adrien Gallouët 2026-03-31 16:18:00 +02:00
  • 632219af73 CANN: fix multi-thread set_tensor race conditions (#20151) b8603 hipudding 2026-03-31 22:00:51 +08:00
  • 4a00bbfed6 server: (webui) no more gzip compression (#21073) b8602 Xuan-Son Nguyen 2026-03-31 15:44:26 +02:00
  • 624733d631 common : gpt-oss handle builtin and unsolicited tool calls (#21213) b8601 Aldehir Rojas 2026-03-31 06:52:42 -05:00
  • 0b6ff47996 fix: correct misspellings in code comments (#21217) b8600 lainon1 2026-03-31 12:50:51 +01:00
  • eec6f85d7b CI: Enable CPU and Vulkan ARM64 Release (#21207) b8599 Seungmin Kim 2026-03-31 20:02:56 +09:00
  • 9281dd135d sync : ggml b8598 Georgi Gerganov 2026-03-31 13:08:13 +03:00
  • 0be6c7c9ce ggml : bump version to 0.9.9 (ggml/1449) Georgi Gerganov 2026-03-30 18:34:29 +03:00
  • 41361c8599 common : move up common_init() and fix Windows UTF-8 logs (#21176) Adrien Gallouët 2026-03-31 12:53:41 +02:00
  • 62278cedde sycl : enhance fattn perf (#21185) b8595 Neo Zhang 2026-03-31 18:31:50 +08:00
  • 90aa83c6bd common: add bounds check in common_init_result::sampler to prevent segfault on failed model load (#21082) mtmcp 2026-03-31 07:04:42 -03:00
  • fcc2d598c8 fix: include API key in CORS proxy requests for MCP connections (#21193) SATISH K C 2026-03-31 03:52:34 -05:00
  • 4453e77561 server/webui: cleanup dual representation approach, simplify to openai-compat (#21090) Piotr Wilkin (ilintar) 2026-03-31 10:42:06 +02:00
  • 26dac845cc vendor : update BoringSSL to 0.20260327.0 (#21211) b8591 Adrien Gallouët 2026-03-31 09:21:54 +02:00
  • 5ce013cd7e common : Disable backend sampling if reasoning budget is enabled (#21209) b8590 Galunid 2026-03-31 09:14:01 +02:00
  • 2985be3324 update hw info enhance_fa arthw 2026-03-31 09:24:40 +08:00
  • 08f21453ae opencl: add q4_K gemm and gemv kernels for Adreno (#20919) b8589 shaofeiqi 2026-03-30 12:19:16 -07:00
  • 84ae8434d0 CI : Enable CUDA and Vulkan ARM64 runners and fix CI/CD (#21122) Seungmin Kim 2026-03-31 03:24:37 +09:00
  • ead417f01c jinja : handle empty expressions correctly (#20913) b8587 Zhihao "Zephyr" Yao 2026-03-30 14:08:46 -04:00