 R0CKSTAR
|
e54c35e4fb
feat: Support Moore Threads GPU (#8383)
|
hai 1 ano |
 slaren
|
2b1f616b20
ggml : reduce hash table reset cost (#8698)
|
hai 1 ano |
 Xuan Son Nguyen
|
be6d7c0791
examples : remove `finetune` and `train-text-from-scratch` (#8669)
|
hai 1 ano |
|
Xuan Son Nguyen
|
de280085e7
examples : Fix `llama-export-lora` example (#8607)
|
hai 1 ano |
 Georgi Gerganov
|
938943cdbf
llama : move vocab, grammar and sampling into separate files (#8508)
|
hai 1 ano |
 Johannes Gäßler
|
5e116e8dd5
make/cmake: add missing force MMQ/cuBLAS for HIP (#8515)
|
hai 1 ano |
 bandoti
|
17eb6aa8a9
vulkan : cmake integration (#8119)
|
hai 1 ano |
 Nicholai Tukanov
|
368645698a
ggml : add NVPL BLAS support (#8329) (#8425)
|
hai 1 ano |
 Clint Herron
|
dd07a123b7
Name Migration: Build the deprecation-warning 'main' binary every time (#8404)
|
hai 1 ano |
|
Georgi Gerganov
|
6b2a849d1f
ggml : move sgemm sources to llamafile subfolder (#8394)
|
hai 1 ano |
 Dibakar Gope
|
0f1a39f343
ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (#5780)
|
hai 1 ano |
|
Clint Herron
|
e500d6135a
Deprecation warning to assist with migration to new binary names (#8283)
|
hai 1 ano |
|
Johannes Gäßler
|
a03e8dd99d
make/cmake: LLAMA_NO_CCACHE -> GGML_NO_CCACHE (#8392)
|
hai 1 ano |
 Brian
|
f7cab35ef9
gguf-hash: model wide and per tensor hashing using xxhash and sha1 (#8048)
|
hai 1 ano |
|
Clint Herron
|
3e2618bc7b
Adding step to `clean` target to remove legacy binary names to reduce upgrade / migration confusion arising from #7809. (#8257)
|
hai 1 ano |
|
Xuan Son Nguyen
|
a27aa50ab7
Add missing items in makefile (#8177)
|
hai 1 ano |
|
slaren
|
c7ab7b612c
make : fix missing -O3 (#8143)
|
hai 1 ano |
|
Georgi Gerganov
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
hai 1 ano |
|
Johannes Gäßler
|
a818f3028d
CUDA: use MMQ instead of cuBLAS by default (#8075)
|
hai 1 ano |
|
slaren
|
95f57bb5d5
ggml : remove ggml_task_type and GGML_PERF (#8017)
|
hai 1 ano |
|
Clint Herron
|
c5a8d4b749
JSON Schema to GBNF integration tests (#7790)
|
hai 1 ano |
 Ulrich Drepper
|
61665277af
Allow compiling with CUDA without CUDA runtime installed (#7989)
|
hai 1 ano |
 0cc4m
|
7c7836d9d4
Vulkan Shader Refactor, Memory Debugging Option (#7947)
|
hai 1 ano |
|
Xuan Son Nguyen
|
0c7b3595b9
Add `cvector-generator` example (#7514)
|
hai 1 ano |
|
slaren
|
f578b86b21
move BLAS to a separate backend (#6210)
|
hai 1 ano |
 Olivier Chafik
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
hai 1 ano |
|
Johannes Gäßler
|
7d1a378b8f
CUDA: refactor mmq, dmmv, mmvq (#7716)
|
hai 1 ano |
|
Georgi Gerganov
|
554c247caf
ggml : remove OpenCL (#7735)
|
hai 1 ano |
|
Georgi Gerganov
|
0cd6bd3483
llama : remove beam search (#7736)
|
hai 1 ano |
 Radoslav Gerganov
|
bde7cd3cd9
llama : offload to RPC in addition to other backends (#7640)
|
hai 1 ano |
