Commit graph

31 commits

Author SHA1 Message Date
Concedo
7a5499e77b added one more backend for clblast noavx2 and clblast failsafe 2025-01-30 22:47:22 +08:00
Concedo
fec3246ca9 make mmap no longer default, archive class.py 2025-01-15 00:38:03 +08:00
Concedo
eee67281be move kcpp params out 2024-09-10 16:30:12 +08:00
Concedo
d71b5477c5 update lite, cleanup, fix interrogate format 2024-08-18 00:48:53 +08:00
Concedo
066e7ac540 minor fixes: colab gpu backend, lite bugs, package python file with embd 2024-07-15 17:36:03 +08:00
Concedo
11f0643fa4 fix pyinstallers 2024-06-27 15:19:44 +08:00
Concedo
2dedea9a74 add to remaining pyinstallers 2024-05-24 16:21:26 +08:00
Concedo
5ce2fdad24 taesd for sdxl, add lora loading done 2024-05-14 23:02:56 +08:00
Concedo
5d15f8f76a vae test 2024-05-14 19:17:01 +08:00
Concedo
3667cc0113 fixed stableui btn (+4 squashed commit)
Squashed commit:

[1d4714f1] update default amount to gen

[6eacba33] updated lite

[033589af] added first ver sdui

[16f66d57] updated lite
2024-05-06 00:55:16 +08:00
Concedo
06e3a6f36e test workflow (+9 squashed commit)
Squashed commit:

[3d1fedab] test workflow

[c26d3a50] test workflow

[70e84f54] test workflow

[3383d040] workflow test

[2262b3c6] workflow test

[cd335d5a] workflow test

[bdbbfaeb] workflow test

[8e9fed4c] testing workflow

[e5b90d66] workflow test
2024-04-11 23:20:08 +08:00
Concedo
0061299cce fixed quant tools not compiling, updated docs 2024-04-06 23:11:05 +08:00
Concedo
ad638285de Merge branch 'master' into concedo_experimental
# Conflicts:
#	Makefile
#	README.md
#	flake.lock
#	ggml-cuda.cu
#	llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-quantize-fns.cpp
2024-02-28 13:41:35 +08:00
Concedo
35c32fd0f2 refactor some old code with batching 2024-02-05 15:54:45 +08:00
Concedo
5b4cef5a60 archived old unused file 2023-10-02 16:57:20 +08:00
Concedo
871009dfab integrated world tokenizer for RWKV 2023-06-13 20:06:19 +08:00
Concedo
6f82e17b7a added MPT support 2023-06-03 16:14:08 +08:00
Concedo
55e0fbf024 wip integrating new rwkv 2023-05-27 22:45:28 +08:00
Concedo
75e4548821 missed out gpt2 2023-05-21 01:44:47 +08:00
Concedo
00da2a5f4e neox is updated 2023-05-17 14:56:54 +08:00
Concedo
90fe9096b4 clean and refactoring pass before supporting newer models for different arch 2023-05-17 11:23:29 +08:00
Concedo
6504150fac just testing cublas 2023-05-15 20:01:22 +08:00
Concedo
e05455f852 fixed wrong sized struct from legacy q8_1, fixed opencl varsize arrays 2023-05-13 23:56:08 +08:00
Concedo
b335f73a60 BACKWARDS COMPAT QUANT SHIM is ready, but upstream model converter is BORKED. BORK BORK. 2023-05-13 01:30:11 +08:00
Concedo
3de34ee492 Merge branch 'master' into concedo_experimental
# Conflicts:
#	CMakeLists.txt
#	Makefile
#	ggml-opencl.c
2023-05-01 12:03:46 +08:00
Concedo
032a171867 integrated q5 formats 2023-04-28 12:58:39 +08:00
Concedo
59fb174678 fixed compile errors, made mmap automatic when lora is selected, added updated quantizers and quantization handling for gpt neox gpt 2 and gptj 2023-04-24 23:20:06 +08:00
Concedo
68898046c2 accidentally added the binaries onto repo again. 2023-04-22 00:41:19 +08:00
Concedo
ea01771dd5 rwkv is done 2023-04-18 20:55:01 +08:00
Concedo
c200b674f4 updated kobold lite, work on rwkv, added exe path to model load params, added launch parameter 2023-04-18 17:36:44 +08:00
Concedo
763ad172c0 arranged files, updated kobold lite, modified makefile for extra link args on linux, started RWKV implementation 2023-04-17 17:31:45 +08:00