| 2023-12-29 |
Peter Sugihara | llama.swiftui : fix infinite loop, ouput timings, buff... |
commit | commitdiff | tree |
| 2023-12-29 |
Georgi Gerganov | scripts : print list of sync commits |
commit | commitdiff | tree |
| 2023-12-29 |
Tamotsu Takahashi | ci : build with CLBlast + ggml-opencl use GGML_API... |
commit | commitdiff | tree |
| 2023-12-29 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2023-12-29 |
bssrdf | ggml : fix some mul mat cases + add tests for src1... |
commit | commitdiff | tree |
| 2023-12-29 |
Georgi Gerganov | scripts : do not sync commits from this repo |
commit | commitdiff | tree |
| 2023-12-28 |
Justine Tunney | Fix OpenAI server sampling w.r.t. temp and seed (#4668) |
commit | commitdiff | tree |
| 2023-12-28 |
manikbhandari | gpt2 : Add gpt2 architecture integration (#4555) |
commit | commitdiff | tree |
| 2023-12-27 |
Nam D. Tran | llama : add AWQ for llama, llama2, mpt, and mistral... |
commit | commitdiff | tree |
| 2023-12-27 |
Daniel Bevenius | finetune : fix output formatting in print_params (... |
commit | commitdiff | tree |
| 2023-12-27 |
Georgi Gerganov | scripts : add sync-ggml-am.sh |
commit | commitdiff | tree |
| 2023-12-27 |
Georgi Gerganov | ggml : fix dot product for ARM (#4630) |
commit | commitdiff | tree |
| 2023-12-27 |
wonjun Jang | Add byte token type when tokenizer.model is not exists... |
commit | commitdiff | tree |
| 2023-12-26 |
slaren | cuda : fix vmm pool with multi GPU (#4620) |
commit | commitdiff | tree |
| 2023-12-26 |
WillCorticesAI | Update comment for AdamW implementation reference.... |
commit | commitdiff | tree |
| 2023-12-26 |
FantasyGmm | Fix new CUDA10 compilation errors (#4635) |
commit | commitdiff | tree |
| 2023-12-25 |
Paul Tsochantaris | Adding Emeltal reference to UI list (#4629) |
commit | commitdiff | tree |
| 2023-12-24 |
slaren | simplify bug issue template (#4623) |
commit | commitdiff | tree |
| 2023-12-24 |
Shintarou Okada | llama : add PLaMo model (#3557) |
commit | commitdiff | tree |
| 2023-12-24 |
slaren | cuda : improve cuda pool efficiency using virtual memor... |
commit | commitdiff | tree |
| 2023-12-23 |
slaren | fallback to CPU buffer if host buffer alloc fails ... |
commit | commitdiff | tree |
| 2023-12-23 |
Samuel Maynard | ci(docker): fix tags in "Build and push docker image... |
commit | commitdiff | tree |
| 2023-12-23 |
Alexey Parfenov | server : allow to specify custom prompt for penalty... |
commit | commitdiff | tree |
| 2023-12-23 |
kalomaze | grammar : check the full vocab only if necessary (opt... |
commit | commitdiff | tree |
| 2023-12-23 |
Johannes Gäßler | CUDA: fixed row rounding for 0 tensor splits (#4594) |
commit | commitdiff | tree |
| 2023-12-22 |
LeonEricsson | lookup : add prompt lookup decoding example (#4484) |
commit | commitdiff | tree |
| 2023-12-22 |
Georgi Gerganov | sync : ggml (fix im2col) (#4591) |
commit | commitdiff | tree |
| 2023-12-22 |
FantasyGmm | cuda : fix jetson compile error (#4560) |
commit | commitdiff | tree |
| 2023-12-22 |
Henrik Forstén | Fix CudaMemcpy direction (#4599) |
commit | commitdiff | tree |
| 2023-12-22 |
slaren | llama : fix platforms without mmap (#4578) |
commit | commitdiff | tree |
| 2023-12-22 |
Herman Semenov | ggml : add comment about backward GGML_OP_DIAG_MASK_INF... |
commit | commitdiff | tree |
| 2023-12-22 |
Michael Kesper | make : add LLAMA_HIP_UMA option (#4587) |
commit | commitdiff | tree |
| 2023-12-22 |
rhuddleston | ci : tag docker image with build number (#4584) |
commit | commitdiff | tree |
| 2023-12-22 |
Deins | readme : add zig bindings (#4581) |
commit | commitdiff | tree |
| 2023-12-22 |
bobqianic | ggml : extend `enum ggml_log_level` with `GGML_LOG_LEVE... |
commit | commitdiff | tree |
| 2023-12-22 |
crasm | llama : add ability to cancel model loading (#4462) |
commit | commitdiff | tree |
| 2023-12-21 |
Georgi Gerganov | ggml : change ggml_scale to take a float instead of... |
commit | commitdiff | tree |
| 2023-12-21 |
Georgi Gerganov | gguf-py : fix broken link |
commit | commitdiff | tree |
| 2023-12-21 |
Georgi Gerganov | gguf : simplify example dependencies |
commit | commitdiff | tree |
| 2023-12-21 |
Samuel Maynard | ci : add `jlumbroso/free-disk-space` to docker workflow... |
commit | commitdiff | tree |
| 2023-12-21 |
slaren | llama : initial ggml-backend integration (#4520) |
commit | commitdiff | tree |
| 2023-12-21 |
Marcus Dunn | llama : allow getting n_batch from llama_context in... |
commit | commitdiff | tree |
| 2023-12-21 |
Finn Voorhees | metal : fix `ggml_metal_log` vargs (#4373) |
commit | commitdiff | tree |
| 2023-12-21 |
Erik Garrison | cuda : ROCm AMD Unified Memory Architecture (UMA) handl... |
commit | commitdiff | tree |
| 2023-12-21 |
arlo-phoenix | ggml-cuda: Fix HIP build by adding define for __trap... |
commit | commitdiff | tree |
| 2023-12-21 |
Jared Van Bortel | common : remove incorrect --model-draft default (#4568) |
commit | commitdiff | tree |
| 2023-12-21 |
Johannes Gäßler | CUDA: mul_mat_id always on GPU for batches >= 32 (... |
commit | commitdiff | tree |
| 2023-12-21 |
Georgi Gerganov | readme : update coding guidelines |
commit | commitdiff | tree |
| 2023-12-21 |
howlger | py : open merges file as 'utf-8' (#4566) |
commit | commitdiff | tree |
| 2023-12-21 |
bobqianic | cuda : better error message for ggml_get_rows (#4561) |
commit | commitdiff | tree |
| 2023-12-21 |
slaren | cuda : replace asserts in wrong architecture checks... |
commit | commitdiff | tree |
| 2023-12-21 |
Johannes Gäßler | llama : disable per-tensor info prints on model load... |
commit | commitdiff | tree |
| 2023-12-21 |
LoganDark | Fix access violation in ggml_cuda_free_data if tensor... |
commit | commitdiff | tree |
| 2023-12-20 |
Johannes Gäßler | CUDA: Faster Mixtral prompt processing (#4538) |
commit | commitdiff | tree |
| 2023-12-19 |
Eric Sommerlade | ggml : fixed check for _MSC_VER (#4535) |
commit | commitdiff | tree |
| 2023-12-18 |
arlo-phoenix | ggml-cuda: Fix HIP build (#4528) |
commit | commitdiff | tree |
| 2023-12-18 |
Georgi Gerganov | llama.swiftui : add tinyllama 1.1B F16 |
commit | commitdiff | tree |
| 2023-12-18 |
Georgi Gerganov | llama.swiftui : add more models |
commit | commitdiff | tree |
| 2023-12-18 |
Ebey Abraham | llama : add phi-2 + fix NeoX rope + ggml_mul_mat_set_pr... |
commit | commitdiff | tree |
| 2023-12-18 |
hankcs | llama : fix try_override for bool_value which always... |
commit | commitdiff | tree |
| 2023-12-18 |
Jared Van Bortel | decode : fix logits_valid for legacy API (#4516) |
commit | commitdiff | tree |
| 2023-12-17 |
Georgi Gerganov | readme : update hot topics |
commit | commitdiff | tree |
| 2023-12-17 |
Georgi Gerganov | llama.swiftui : add bench functionality (#4483) |
commit | commitdiff | tree |
| 2023-12-17 |
Jared Van Bortel | gguf-py : fail fast on nonsensical special token IDs... |
commit | commitdiff | tree |
| 2023-12-17 |
Matheus Gabriel... | build : Check the ROCm installation location (#4485) |
commit | commitdiff | tree |
| 2023-12-17 |
slaren | finetune : keep allocs alive until all allocations... |
commit | commitdiff | tree |
| 2023-12-17 |
olexiyb | server : disable llm logs if SERVER_VERBOSE is off... |
commit | commitdiff | tree |
| 2023-12-17 |
AdithyanI | server : fix grammar being ignored (#4494) |
commit | commitdiff | tree |
| 2023-12-17 |
Alexey Parfenov | server : fix possible ambiguity in content type charset... |
commit | commitdiff | tree |
| 2023-12-17 |
mzcu | server : allow requests larger than 8K (#4500) |
commit | commitdiff | tree |
| 2023-12-17 |
Bach Le | Link to cublas dynamically on Windows even with LLAMA_S... |
commit | commitdiff | tree |
| 2023-12-16 |
slaren | lora : add support for non-llama models (#3333) |
commit | commitdiff | tree |
| 2023-12-16 |
Jared Van Bortel | llama : sanity checks for access to logits (#4274) |
commit | commitdiff | tree |
| 2023-12-15 |
ShadovvBeast | server : add optional API Key Authentication example... |
commit | commitdiff | tree |
| 2023-12-15 |
slaren | ggml : group mul_mat_id rows by matrix (cpu only) ... |
commit | commitdiff | tree |
| 2023-12-14 |
slaren | ggml : use ggml_row_size where possible (#4472) |
commit | commitdiff | tree |
| 2023-12-14 |
slaren | ggml : remove n_dims from ggml_tensor (#4469) |
commit | commitdiff | tree |
| 2023-12-14 |
wonjun Jang | py : add protobuf dependency (#4466) |
commit | commitdiff | tree |
| 2023-12-14 |
LostRuins | ggml : add ggml_row_size() (fixes llama out of space... |
commit | commitdiff | tree |
| 2023-12-14 |
Georgi Gerganov | ggml : fix OpenCL broadcast requirement for ggml_mul... |
commit | commitdiff | tree |
| 2023-12-14 |
wonjun Jang | convert : support loading vocab from fast tokenizer... |
commit | commitdiff | tree |
| 2023-12-14 |
BarfingLemurs | readme : update supported model list (#4457) |
commit | commitdiff | tree |
| 2023-12-13 |
shibe2 | server : fix handling of characters that span multiple... |
commit | commitdiff | tree |
| 2023-12-13 |
Georgi Gerganov | sync : ggml (SD ops, tests, kernels) (#4444) |
commit | commitdiff | tree |
| 2023-12-13 |
Jared Van Bortel | build : detect host compiler and cuda compiler separate... |
commit | commitdiff | tree |
| 2023-12-13 |
Siwen Yu | common : add `--version` option to show build info... |
commit | commitdiff | tree |
| 2023-12-13 |
Georgi Gerganov | readme : update hot topics |
commit | commitdiff | tree |
| 2023-12-13 |
slaren | llama : add Mixtral support (#4406) |
commit | commitdiff | tree |
| 2023-12-12 |
kalomaze | server : tweak default sampling parameters (#4367) |
commit | commitdiff | tree |
| 2023-12-12 |
Richard Kiss | english : use `typos` to fix comments and logs (#4354) |
commit | commitdiff | tree |
| 2023-12-12 |
Jared Van Bortel | build : target Windows 8 for standard mingw-w64 (#4405) |
commit | commitdiff | tree |
| 2023-12-12 |
crasm | llama : document logits_all deprecation (#4418) |
commit | commitdiff | tree |
| 2023-12-12 |
Vladimir Zorin | server : fix local model name in server (#4420) |
commit | commitdiff | tree |
| 2023-12-12 |
Taikono-Himazin | ggml : increased GGML_MAX_PARAMS to allow finetuning... |
commit | commitdiff | tree |
| 2023-12-10 |
Yueh-Po Peng | Update README.md (#4388) |
commit | commitdiff | tree |
| 2023-12-09 |
Xiang (Kevin) Li | grammar : revert the replacement of llama_token_to_piec... |
commit | commitdiff | tree |
| 2023-12-07 |
Georgi Gerganov | sync : ggml (new ops, tests, backend, etc.) (#4359) |
commit | commitdiff | tree |
| 2023-12-07 |
Georgi Gerganov | llama : per-layer KV cache + quantum K cache (#4309) |
commit | commitdiff | tree |
| 2023-12-07 |
Hongyu Ouyang | train : fix #4227 (double free in examples/train-text... |
commit | commitdiff | tree |
| 2023-12-06 |
Georgi Gerganov | server : recognize cache_prompt parameter in OAI API... |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / llama.cpp / shortlog