mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

Commit Graph

  • 42ebce3beb common : fix get_gguf_split_info (#20946) Adrien Gallouët 2026-03-24 13:33:14 +01:00
  • a94fdb090a WebUI: fix edit msg form textarea height (#20830) BlueMöhre 2026-03-24 13:17:45 +01:00
  • c9dc43333f readme : clarify MODEL_ENDPOINT usage (#20941) Adrien Gallouët 2026-03-24 10:35:07 +01:00
  • 2d2d9c2062 common : add a WARNING for HF cache migration (#20935) Adrien Gallouët 2026-03-24 09:24:39 +01:00
  • 92080b4396 metal : add FLOOR, CEIL, ROUND, TRUNC unary ops (#20930) nuri 2026-03-24 17:13:07 +09:00
  • 342d6125bc metal : add FA instantiations for HSK=512, HSV=512 (#20902) Georgi Gerganov 2026-03-24 10:03:09 +02:00
  • c2e224d829 issues: add openvino backends (#20932) Aaron Teo 2026-03-24 14:41:10 +08:00
  • 8c7957ca33 common : add standard Hugging Face cache support (#20775) Adrien Gallouët 2026-03-24 07:30:33 +01:00
  • e852eb4901 llama-fit: fix regex pattern for gate_up tensors (#20910) Aman Gupta 2026-03-24 12:57:57 +08:00
  • 312d870a89 common : replace wrap_for_generation with a prefix convenience function and fix gpt-oss (#20912) Aldehir Rojas 2026-03-23 22:21:47 -05:00
  • 7cadbfce10 hexagon: general DMA and Binary Op fixes for large strides (#20918) Max Krasnyansky 2026-03-23 15:33:49 -07:00
  • 1fb2290a51 Add codeowners for scripts/snapdragon and docs/snapdragon (#20915) Max Krasnyansky 2026-03-23 14:57:18 -07:00
  • 1772701f99 opencl: add q6_K gemm and gemv kernels for Adreno (#20089) lhez 2026-03-23 12:44:18 -07:00
  • 39bf0d3c6a rpc : RCE patch (#20908) las7 2026-03-23 10:54:57 -07:00
  • bd6992180b contrib: add "Requirements" section to PR template (#20841) Xuan-Son Nguyen 2026-03-23 16:59:02 +01:00
  • fd18364755 devops: upgraded default oneAPI version (#20731) Davi Henrique Linhares 2026-03-23 10:47:34 -03:00
  • 11fb11b901 webui: Improve chat form positioning (#20901) Aleksander Grygier 2026-03-23 14:30:55 +01:00
  • 35b662bb5d docs: Fix typo in reasoning flag documentation (#20780) Geo Maciolek 2026-03-23 09:24:55 -04:00
  • f93c09e267 memory : fix seq_id bounds in llama_memory_recurrent::state_read_meta() (#20887) Georgi Gerganov 2026-03-23 14:08:46 +02:00
  • 841bc203e2 docs : rerun llama-gen-docs to include new CLI args (#20892) Eric Zhang 2026-03-23 19:33:38 +08:00
  • 31a5cf4c3f server: use httplib dynamic threads (#20817) Xuan-Son Nguyen 2026-03-23 12:22:46 +01:00
  • e32d243849 ai : update gh permissions (#20895) Georgi Gerganov 2026-03-23 13:21:41 +02:00
  • c44a932cf4 webui: fix --webui-config-file settings not applied on load (#20823) Pascal 2026-03-23 11:25:35 +01:00
  • 177c75852a metal: add CONV_3D (#19927) Rashid Ul Islam 2026-03-23 13:15:34 +05:30
  • 7a0b6a635e common/autoparser : detect reasoning markers when enable_thinking changes system prompt (#20859) Jhen-Jie Hong 2026-03-23 15:35:27 +08:00
  • 07ff000551 CANN: add RoPE cache preload before ACL graph capture (#20747) Chenguang Li 2026-03-23 15:24:06 +08:00
  • cc18f965b6 fix(openvino): explicit memset in buffer_context allocation (#20857) Dan Hoffman 2026-03-22 23:05:37 -07:00
  • 84ffd0c192 opencl: add flattened Q4_K mv and general Q4_K mm (#20773) shaofeiqi 2026-03-22 22:45:11 -07:00
  • ec2b787ebe mtmd: Add dynamic high-resolution image preprocessing for InternVL model (#20847) bssrdf 2026-03-22 20:06:30 -04:00
  • d3ac030a5d mtmd : fix LightOnOCR image preprocessing (#20877) DorianRudolph 2026-03-23 01:04:14 +01:00
  • 49bfddeca1 server: allow router to report child instances sleep status (#20849) Xuan-Son Nguyen 2026-03-22 18:33:52 +01:00
  • bd3f1d9d65 CUDA: fix BF16 FA compilation (#20865) Johannes Gäßler 2026-03-22 17:53:33 +01:00
  • 23c9182ce8 jinja : refactor token advancement (#20864) Sigbjørn Skjæret 2026-03-22 17:45:10 +01:00
  • 81bc4d3ddc server: fix Host header (#20843) Evgeny Kurnevsky 2026-03-22 15:29:22 +01:00
  • f40a80b4f3 support bf16 and quantized type (#20803) Neo Zhang 2026-03-22 22:06:27 +08:00
  • db9d8aa428 ggml-cuda: native bf16 flash attention for vec kernel (#20525) Patrick Buckley 2026-03-22 03:05:51 -07:00
  • ccb87fa3ee [CUDA] Increase number of output elements per-thread block if the K-dimension is small (#20635) Gaurav Garg 2026-03-22 14:19:35 +05:30
  • 3306dbaef7 misc : prefer ggml-org models in docs and examples (#20827) ddh0 2026-03-21 16:00:26 -05:00
  • 990e4d9698 common/grammar: fix grammar parsing issues to prevent stack overflow and hangs (#18604) Andrea Arcangeli 2026-03-21 13:43:35 -04:00
  • 212f4521b0 context : use n_embd_out for pooled embedding extraction (#20840) Tom Hillbrunner 2026-03-21 18:35:00 +01:00
  • 568aec82d2 docs : explicit about banning accounts that violates policy (#19593) Xuan-Son Nguyen 2026-03-21 15:50:16 +01:00
  • 2bcdddd5e3 fix(rpc): prevent division by zero in deserialize_tensor (#20712) y198 2026-03-21 20:59:43 +07:00
  • eac9c6ea83 Convert: Make NVFP4 and MXFP4 HF conversions say NVFP4/MXFP4 instead of BF16 (#20730) Michael Wand 2026-03-21 04:35:21 -07:00
  • 29b28a9824 ci : switch from pyright to ty (#20826) Sigbjørn Skjæret 2026-03-21 08:54:34 +01:00
  • cea560f483 Add shader count for Intel Arc Pro B60 (#20818) Matt Corallo 2026-03-21 04:22:51 +00:00
  • b1c70e2e54 common/parser: fix nasty bug causing subtle corruption of generation prompt (#20825) Piotr Wilkin (ilintar) 2026-03-21 00:19:04 +01:00
  • e6ec21e62f ggml-cpu: add always_inline to tinyBLAS_PPC accumulator saves (#20791) shalinib-ibm 2026-03-21 04:41:45 +05:30
  • 4cb7e0bd61 ai : limit runtime of the agent (#20816) Georgi Gerganov 2026-03-20 20:31:25 +02:00
  • 149b2493c0 common : fix typo in debug log ('extracft' -> 'extract') (#20807) James O'Leary 2026-03-20 10:23:18 -07:00
  • b31b30f31d ai : do not run bash commands in the prompt (#20810) Georgi Gerganov 2026-03-20 19:06:33 +02:00
  • 58c81f7e81 model : fix Granite Hybrid type check for 7B.A1B (#20795) Victor Villar 2026-03-20 15:16:09 +01:00
  • fb78ad29bb server: (doc) clarify in-scope and out-scope features (#20794) Xuan-Son Nguyen 2026-03-20 14:03:50 +01:00
  • e06c3ab2bc vulkan: change gated_delta_net to shard a column across a subgroup (#20662) Jeff Bolz 2026-03-20 06:17:15 -05:00
  • dc6592431b context: zero output buffer on allocation (#20781) Ruikai Peng 2026-03-20 17:31:34 +08:00
  • 3adbef7776 model: assert nextn_predict_layers to prevent underflow (#20783) Ruikai Peng 2026-03-20 17:17:58 +08:00
  • ab9d4c3678 server : improve mtmd ctx checkpoints (#20726) Georgi Gerganov 2026-03-20 11:13:12 +02:00
  • 1af9dab32b CANN: add BF16 support for core operators (#20152) hipudding 2026-03-20 17:08:39 +08:00
  • 6d99b44c7e docs : fix Metal backend op support status in ops.md (#20779) Seyoung Jeong 2026-03-20 03:06:38 -06:00
  • 464fd0e71f ai : update find-related action (#20790) Georgi Gerganov 2026-03-20 10:28:14 +02:00
  • 21c8045214 jinja : fix heap OOB read in value equality comparison (#20782) Ruikai Peng 2026-03-20 14:15:17 +08:00
  • c46583b86b common/parser : fix out_of_range crash in throw path (#20424 regression) (#20777) James O'Leary 2026-03-19 18:37:22 -07:00
  • c1b911654a server: fix router mode deadlock on child crash and TOCTOU race in models_max (#20763) Ben Racicot 2026-03-19 17:16:05 -04:00
  • b739738dad docs: Update server README to reflect PR #20297 (#20560) Tomeamis 2026-03-19 21:28:44 +01:00
  • a0bbcdd9b6 ggml: guard KleidiAI DOWNLOAD_EXTRACT_TIMESTAMP for cmake < 3.24 (#20767) Sundaram krishnan 2026-03-20 01:06:23 +05:30
  • 6c72646a61 ci : improve action for duplicate issue (#20772) Georgi Gerganov 2026-03-19 21:11:53 +02:00
  • 340807273b hip: Avoid compiler bug in RDNA code generation during debug builds on Windows (#20655) Rail Chabdarov 2026-03-19 19:14:08 +01:00
  • 26c9ce1288 server: Add cached_tokens info to oaicompat responses (#19361) Ryan Goulden 2026-03-19 11:09:33 -07:00
  • 76f2dc70c3 chat : handle tool calls with no required args in TAG_WITH_TAGGED format (#20764) James O'Leary 2026-03-19 09:53:11 -07:00
  • 900efd531d ci : clarify gh command for viewing issues (#20766) Georgi Gerganov 2026-03-19 18:43:54 +02:00
  • 74c42ee1f4 hexagon: add Matrix Extensions (HMX) for Hexagon NPU backend (#20693) Yiwei Shao 2026-03-19 09:11:06 -07:00
  • b49d8b8757 ci : add hip quality check (#20430) uvos 2026-03-19 17:05:44 +01:00
  • 5e54d51b19 common/parser: add proper reasoning tag prefill reading (#20424) Piotr Wilkin (ilintar) 2026-03-19 16:58:21 +01:00
  • c1258830b2 ggml webgpu: ops support for qwen3.5 (SET, TRI_SOLVE, SSM_CONV, GATED_DELTA_NET) + GET_ROWS optimization (#20687) Reese Levine 2026-03-19 08:45:28 -07:00
  • 922b90e567 common : add LLAMA_ARG_SPEC_TYPE (#20744) ddh0 2026-03-19 10:16:55 -05:00
  • f071ce67c9 ci : add action for finding duplicate issues (#20756) Georgi Gerganov 2026-03-19 16:17:37 +02:00
  • 4065c1a3a6 Server becomes the source of truth for sampling parameter defaults (#20558) Pascal 2026-03-19 13:20:39 +01:00
  • 1e64534570 mtmd: add clip_graph::build_mm() (#20751) Xuan-Son Nguyen 2026-03-19 13:11:39 +01:00
  • cd708db0cc WebUI: Persist the on/off state of the MCP servers for new conversations (#20750) Pascal 2026-03-19 12:54:06 +01:00
  • 512bba6ee0 webui: Improve model parsing logic + add unit tests (#20749) Aleksander Grygier 2026-03-19 12:25:50 +01:00
  • b486c17b3e convert : support is_causal hyperparameter (#20746) Dowon 2026-03-19 19:41:11 +09:00
  • 1b9bbaa357 common : fix gpt-oss content removal (#20745) Aldehir Rojas 2026-03-19 05:40:39 -05:00
  • 07feeaa92e vulkan: dequantize iq4_xs 4 at a time (#20657) Eve 2026-03-19 10:32:04 +00:00
  • 3fee84e156 cmake : fix build warning when kleidiai is enabled (#20457) Charles Xu 2026-03-19 09:14:48 +01:00
  • 811397745e vocab : assert array size of scores and toktypes (#20737) Sigbjørn Skjæret 2026-03-19 08:34:04 +01:00
  • c014c3f83a docs: add information about openvino in the docker page (#20743) Kevin Hannon 2026-03-19 03:08:47 -04:00
  • 7f2cbd9a4d CANN: handle in-place ROPE on non-contiguous f32 tensors (#20274) Chenguang Li 2026-03-19 14:05:01 +08:00
  • 509a31d00f ggml-webgpu: Update the RMS_NORM preprocessor and add L2_NORM (#20665) Masashi Yoshimura 2026-03-19 13:08:59 +09:00
  • ea01d196d7 ggml-webgpu: Add supports for DIAG and TRI (#20664) Masashi Yoshimura 2026-03-19 13:08:35 +09:00
  • 07ba6d275b CANN: support flash attention for head dim not multiple of 16, fix ALiBi slope offset (#20031) Chenguang Li 2026-03-19 11:02:42 +08:00
  • 6729d4920c model : add control vector support where missing (#20653) Michael Grau 2026-03-18 23:25:12 +01:00
  • d13d60af1d gguf-py : cleaner way to get the first key (#20727) Sigbjørn Skjæret 2026-03-18 23:21:42 +01:00
  • 5744d7ec43 Rebuild index.html.gz (#20724) crsawyer 2026-03-18 12:49:57 -05:00
  • 8ced5f41f9 Move to no timeout for WaitAny in graph submission to avoid deadlocks in some cases on llvm-pipe backends (#20618) Reese Levine 2026-03-18 10:23:47 -07:00
  • 78d550b541 ggml-cpu/x86: fix unused changemask warning in repack (#20692) Shaw Nguyen 2026-03-18 23:45:06 +07:00
  • 4efd326e71 sync : ggml Georgi Gerganov 2026-03-18 14:45:54 +02:00
  • b08f7322ee ggml : bump version to 0.9.8 (ggml/1442) Georgi Gerganov 2026-03-16 20:15:14 +02:00
  • 79187f2fb8 ggml : restore ggml_type_sizef() to aboid major version bump (ggml/1441) Georgi Gerganov 2026-03-16 20:09:25 +02:00
  • 48e61238e1 webui: improve tooltip wording for attachment requirements (#20688) Julien Chaumond 2026-03-18 14:01:02 +01:00
  • 312cf03328 llama : re-enable manual LoRA adapter free (#19983) Pop Flamingo 2026-03-18 11:03:26 +01:00
  • f4049ad735 tests : fix test-jinja-py Windows failures by bypassing command-line args [no ci] (#20483) Masato Nakasaka 2026-03-18 02:43:31 -07:00