]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2024-01-11 Behnam Mserver : update readme to document the new `/health...
2024-01-11 Georgi Gerganovserver : fix build + rename enums (#4870)
2024-01-10 Behnam Mserver : add a `/health` endpoint (#4860)
2024-01-10 Brianllama : add additional suffixes for model params (...
2024-01-10 Austinllama : recognize 1B phi models (#4847)
2024-01-10 Johnclip : support more quantization types (#4846)
2024-01-10 Johannes GäßlerPython script to compare commits with llama-bench ...
2024-01-09 Austinconvert.py : fix vanilla LLaMA model conversion (#4818)
2024-01-09 Justine Tunneyllava-cli : don't crash if --image flag is invalid...
2024-01-09 Georgi Gerganovmetal : improve dequantize precision to match CPU ...
2024-01-09 Georgi Gerganovscripts : improve get-pg.sh (#4838)
2024-01-09 iohubreadme : add 3rd party collama reference to UI list...
2024-01-09 Georgi Gerganovscripts : script to get Paul Graham essays in txt forma...
2024-01-09 Behnam Mserver : update readme about token probs (#4777)
2024-01-09 Zsapiserver : add api-key flag to documentation (#4832)
2024-01-09 Georgi Gerganovggml : fix vld1q_s8_x4 32-bit compat (#4828)
2024-01-09 Johannes GäßlerCUDA: faster softmax via shared memory + fp16 math...
2024-01-08 howlgercommon : fix the short form of `--grp-attn-w`, not...
2024-01-08 Georgi Gerganovreadme : add link to SOTA models
2024-01-08 KawrakowSOTA 2-bit quants (#4773)
2024-01-08 Georgi Gerganovswift : exclude ggml-metal.metal from the package ...
2024-01-08 Georgi Gerganovllama.swiftui : update readme
2024-01-08 Georgi Gerganovmain : add self-extend support (#4815)
2024-01-08 Georgi Gerganovexamples : add passkey test (#3856)
2024-01-07 Lars Grammelreadme : add lgrammel/modelfusion JS/TS client for...
2024-01-07 slarenllama-bench : add no-kv-offload parameter (#4812)
2024-01-07 Johannes GäßlerCUDA: fixed redundant value dequantization (#4809)
2024-01-07 Georgi Gerganovllama : remove unused vars (#4796)
2024-01-07 Georgi Gerganovllama : remove redundant GQA check (#4796)
2024-01-07 Alex Azarovllama.swiftui : use llama.cpp as SPM package (#4804)
2024-01-07 Georgi Gerganovllama : print tensor meta for debugging
2024-01-07 Alex Azarovllama.swiftui : add visionOS target (#4805)
2024-01-07 Konstantin... ggml : use __builtin_amdgcn_sudot4 in __dp4a for gfx11...
2024-01-07 Georgi Gerganovserver : fix n_predict check (#4798)
2024-01-06 Daniel Illescas... llama.swiftui : use correct pointer for llama_token_eos...
2024-01-06 Georgi Gerganovexamples : improve base-translate.sh script (#4783)
2024-01-05 a-n-n-a-l-e-ecmake : check for openblas64 (#4134)
2024-01-05 Ikko Eltociear... flake.nix : fix typo (#4700)
2024-01-05 Georgi Gerganovmetal : switch back to default.metallib (ggml/681)
2024-01-05 Georgi Gerganovggml : fix q2_k bpw in comments (ggml/680)
2024-01-05 Finn Voorheesggml : add error handling to graph_compute (whisper...
2024-01-05 Georgi Gerganovggml : do not sched_yield when calling BLAS (#4761)
2024-01-05 Georgi Gerganovexamples : add few-shot translation example (#4783)
2024-01-04 Daniel Beveniusfinetune : remove unused includes (#4756)
2024-01-04 Georgi Gerganovserver : send token probs for "stream == false" (#4714)
2024-01-04 Johannes GäßlerPrint backend name on test-backend-ops failure (#4751)
2024-01-04 singularityllama.swiftui : support loading custom model from file...
2024-01-04 Michael Coppolaserver : fix options in README.md (#4765)
2024-01-04 Georgi Gerganovggml : include stdlib.h before intrin.h (#4736)
2024-01-04 singularityllama.swiftui : fix build of ggml.metallib (#4754)
2024-01-03 Daniel Beveniustrain : fix typo in overlapping-samples help msg (...
2024-01-03 Ashraful Islamswift : update Package.swift to use ggml as dependency...
2024-01-03 Georgi Gerganovcuda : simplify expression
2024-01-03 Georgi Gerganovcuda : mark I16 and I32 ops as unsupported
2024-01-03 Georgi Gerganovsync : ggml
2024-01-03 Georgi Gerganovmetal : add kernel_get_rows_i32
2024-01-03 Georgi Gerganovscripts : fix sync order + metal sed
2024-01-03 Guillaume Wenzekggml : extend ggml_get_rows, ggml_repeat, ggml_concat...
2024-01-03 Justin Parkerserver : throw an error when `slot unavailable` (#4741)
2024-01-02 Georgi Gerganovmetal : optimize ggml_mul_mat_id (faster Mixtral PP...
2024-01-02 Phil Hserver : add token counts to html footer (#4738)
2024-01-02 Georgi Gerganovllama : llama_model_desc print number of experts
2024-01-02 Marcus Dunnllama : replace all API facing `int`'s with `int32_t...
2024-01-02 postmastersllama : differentiate the KV dims in the attention...
2024-01-02 Georgi Gerganoveditorconfig : fix whitespace and indentation #4710
2024-01-02 minarchistserver : add --override-kv parameter (#4710)
2024-01-02 Nam D. Tranpy : re-enable mmap in convert hf (#4732)
2024-01-02 Daniel Beveniusfinetune: fix typo in README.md (#4733)
2024-01-02 Georgi Gerganovmetal : enable shader debugging (cmake option) (#4705)
2023-12-31 Someone Sergeflake.lock: update
2023-12-31 Someone Sergeflake.nix: suggest the binary caches
2023-12-31 Someone Sergeworkflows: nix-ci: add a qemu job for jetsons
2023-12-31 Someone Sergeworkflows: nix-flakestry: drop tag filters
2023-12-31 Someone Sergeworkflows: weekly `nix flake update`
2023-12-31 Someone Sergeworkflows: nix-ci: add a job for eval
2023-12-31 Someone Sergeworkflows: nix-ci: init; build flake outputs
2023-12-31 Someone Sergeflake.nix: expose checks
2023-12-31 Someone Sergeflake.nix: rocm not yet supported on aarch64, so hide...
2023-12-31 Someone Sergeflake.nix: expose full scope in legacyPackages
2023-12-31 Georgi Gerganovggml : add ggml_vdotq_s32 alias (#4715)
2023-12-30 Georgi Gerganovclip : refactor + bug fixes (#4696)
2023-12-30 Johannes GäßlerCUDA: fixed tensor cores not being used on RDNA3 (...
2023-12-30 automaticcatggml : add ggml_cpu_has_avx_vnni() (#4589)
2023-12-29 Johannes GäßlerCUDA: fix tensor core logic for Pascal and HIP (#4682)
2023-12-29 Georgi Gerganovclip : use ggml_backend_buffer_is_host (#4205)
2023-12-29 Steward Garciaclip : enable gpu backend (#4205)
2023-12-29 hydaicuda: fix vmm oom issue on NVIDIA AGX Orin (#4687)
2023-12-29 crasmpython : add check-requirements.sh and GitHub workflow...
2023-12-29 Philip Taronflake.nix : rewrite (#4605)
2023-12-29 Cuong Trinh... cmake : fix ld warning duplicate libraries libllama...
2023-12-29 Justine Tunneyllava-cli : refactor to use sampling library (#4669)
2023-12-29 Justine Tunneyserver : replace sleep with condition variables (#4673)
2023-12-29 SakuraUmiserver : fix OpenAI server sampling w.r.t. penalty...
2023-12-29 Karthik Sethuramanserver : allow to generate multimodal embeddings (...
2023-12-29 andrijdavidmain-cmake-pkg : fix build issue (#4665)
2023-12-29 Peter Sugiharallama.swiftui : fix infinite loop, ouput timings, buff...
2023-12-29 Georgi Gerganovscripts : print list of sync commits
2023-12-29 Tamotsu Takahashici : build with CLBlast + ggml-opencl use GGML_API...
2023-12-29 Georgi Gerganovsync : ggml
2023-12-29 bssrdfggml : fix some mul mat cases + add tests for src1...
next