koboldcpp/otherarch
Concedo 6b7d2349a7 Rewrite history to fix bad vulkan shader commits without increasing repo size
added dpe colab (+8 squashed commit)

Squashed commit:

[b8362da4] updated lite

[ed6c037d] move nsigma into the regular sampler stack

[ac5f61c6] relative filepath fixed

[05fe96ab] export template

[ed0a5a3e] nix_example.md: refactor (#1401)

* nix_example.md: add override example

* nix_example.md: drop graphics example, already basic nixos knowledge

* nix_example.md: format

* nix_example.md: Vulkan is disabled on macOS

Disabled in: 1ccd253acc

* nix_examples.md: nixpkgs.config.cuda{Arches -> Capabilities}

Fixes: https://github.com/LostRuins/koboldcpp/issues/1367

[675c62f7] AutoGuess: Phi 4 (mini) (#1402)

[4bf56982] phrasing

[b8c0df04] Add Rep Pen to Top N Sigma sampler chain (#1397)

- place after nsigma and before xtc (+3 squashed commit)

Squashed commit:

[87c52b97] disable VMM from HIP

[ee8906f3] edit description

[e85c0e69] Remove Unnecessary Rep Counting (#1394)

* stop counting reps

* fix range-based initializer

* strike that - reverse it
2025-03-05 00:02:20 +08:00
..
sdcpp merge sd fix 2025-02-21 11:16:26 +08:00
tools added one more backend for clblast noavx2 and clblast failsafe 2025-01-30 22:47:22 +08:00
whispercpp quiet flags now set at load time 2025-01-25 16:46:56 +08:00
ggml_v1.c
ggml_v1.h
ggml_v2-cuda-legacy.cu attempts a backflip, but does he stick the landing? 2024-11-16 17:05:45 +08:00
ggml_v2-cuda-legacy.h
ggml_v2-cuda.cu attempts a backflip, but does he stick the landing? 2024-11-16 17:05:45 +08:00
ggml_v2-cuda.h
ggml_v2-opencl-legacy.c
ggml_v2-opencl-legacy.h
ggml_v2-opencl.cpp
ggml_v2-opencl.h
ggml_v2.c Merge commit '280345968d' into concedo_experimental 2024-04-07 20:27:17 +08:00
ggml_v2.h
ggml_v3-cuda.cu cleaned up unused flags from makefile, updated lite 2025-01-30 19:34:55 +08:00
ggml_v3-cuda.h attempts a backflip, but does he stick the landing? 2024-11-16 17:05:45 +08:00
ggml_v3-opencl.cpp
ggml_v3-opencl.h
ggml_v3.c try fix compile issues 2024-09-19 13:56:19 +08:00
ggml_v3.h Fixed some GGUFv1 loading bugs, long overdue cleanup for compiling, integrated TTS 2025-01-13 14:23:25 +08:00
ggml_v3b-opencl.cpp You'll never take us alive 2025-01-09 11:27:06 +08:00
ggml_v3b-opencl.h clean and rename old clblast files in preparation for merge 2024-12-15 15:29:02 +08:00
gpt2_v1.cpp
gpt2_v2.cpp
gpt2_v3.cpp Merge commit '280345968d' into concedo_experimental 2024-04-07 20:27:17 +08:00
gptj_v1.cpp
gptj_v2.cpp
gptj_v3.cpp Merge commit '280345968d' into concedo_experimental 2024-04-07 20:27:17 +08:00
llama-util.h Merge commit '280345968d' into concedo_experimental 2024-04-07 20:27:17 +08:00
llama_v2-util.h Merge commit '280345968d' into concedo_experimental 2024-04-07 20:27:17 +08:00
llama_v2.cpp added a nicer built in voice 2025-01-13 23:26:54 +08:00
llama_v2.h Fixed some GGUFv1 loading bugs, long overdue cleanup for compiling, integrated TTS 2025-01-13 14:23:25 +08:00
llama_v3.cpp added a nicer built in voice 2025-01-13 23:26:54 +08:00
llama_v3.h Merge commit '280345968d' into concedo_experimental 2024-04-07 20:27:17 +08:00
mpt_v3.cpp Merge commit '280345968d' into concedo_experimental 2024-04-07 20:27:17 +08:00
neox_v2.cpp
neox_v3.cpp Merge commit '280345968d' into concedo_experimental 2024-04-07 20:27:17 +08:00
otherarch.h Rewrite history to fix bad vulkan shader commits without increasing repo size 2025-03-05 00:02:20 +08:00
rwkv_v2.cpp Fixed some GGUFv1 loading bugs, long overdue cleanup for compiling, integrated TTS 2025-01-13 14:23:25 +08:00
rwkv_v2.h
rwkv_v3.cpp added llava letterboxing feature 2024-08-25 23:15:38 +08:00
rwkv_v3.h
rwkv_vocab.cpp vae test 2024-05-14 19:17:01 +08:00
tts_adapter.cpp remove tts audio caching 2025-02-12 11:37:43 +08:00
utils.cpp ensure scale before rep pen 2025-02-09 16:59:56 +08:00
utils.h improved sampling for tts and fixed yet another bug. no patch release for this. 2025-01-23 23:37:13 +08:00