 Frank Mai
|
b96f9afb0d
chore: clean useless beam search param (#7985)
|
1 year ago |
 Abheek Gulati
|
1193778105
readme : update UI list (#7943)
|
1 year ago |
 Georgi Gerganov
|
5326bcceeb
ggml : sync
|
1 year ago |
|
Georgi Gerganov
|
e6ecc2be47
whisper : use ggml_backend_sched (whisper/2239)
|
1 year ago |
 Ștefan-Gabriel Muscalu
|
a94e6ff877
update: support Qwen2-57B-A14B (#7835)
|
1 year ago |
 Srihari-mcw
|
5b6da18750
Make updates to type cast based on compiler instead of OS (#7851)
|
1 year ago |
|
Georgi Gerganov
|
7c26775adb
llama : disable FA if KV head size do not match (#7982)
|
1 year ago |
 Bryan Honof
|
b473e95084
Add Nix and Flox install instructions (#7899)
|
1 year ago |
 slaren
|
99052cd227
sched : offload_op also requires supports_op (#7977)
|
1 year ago |
|
Frank Mai
|
c637fcd34d
fix: divide 0 exception in mamba (#7932)
|
1 year ago |
 Markus Tavenrath
|
6a2f0b3474
Implement non-mapped async IO for CUDA on Windows. (#7896)
|
1 year ago |
|
Georgi Gerganov
|
21be9cab94
rpc : fix load/store misaligned addresses (#7948)
|
1 year ago |
 Brian
|
006167aaf6
gguf-dump.py: add --markdown dump output (#7853)
|
1 year ago |
 Neo Zhang
|
df68d4fa5d
[SYCL] Update README-sycl.md for Chapter "Recommended release" and "News" (#7946)
|
1 year ago |
 Calvin Laurenson
|
43b35e38ba
Add support for sqrt on CUDA (#7953)
|
1 year ago |
|
Georgi Gerganov
|
19b7a836f6
cuda : fix bounds check for src0 rows in MMVQ kernel (whisper/2231)
|
1 year ago |
 Hong Bo PENG
|
b5fcf8ef5c
ggml : fix and optimize ppc64le (ggml/849)
|
1 year ago |
 Daniel Bevenius
|
398105ff43
ggml : remove duplicate include of ggml-common.h (ggml/853)
|
1 year ago |
|
Georgi Gerganov
|
bc6c457fa3
flake.lock: Update (#7951)
|
1 year ago |
|
Georgi Gerganov
|
52399254b3
unicode : avoid char32_t (#7957)
|
1 year ago |
 hopkins385
|
6fe1c62741
readme : update UI list [no ci] (#7958)
|
1 year ago |
|
Georgi Gerganov
|
cddaf028ad
ggml : fix handling of zero blocks in IQ quants (#7955)
|
1 year ago |
|
Georgi Gerganov
|
c8a82194a8
github : update pr template
|
1 year ago |
 0cc4m
|
7c7836d9d4
Vulkan Shader Refactor, Memory Debugging Option (#7947)
|
1 year ago |
 Xuan Son Nguyen
|
0c7b3595b9
Add `cvector-generator` example (#7514)
|
1 year ago |
 Meng, Hengyu
|
7b2f4a7d19
[SYCL] remove global variables (#7710)
|
1 year ago |
 olexiyb
|
f8ec8877b7
ci : fix macos x86 build (#7940)
|
1 year ago |
 Johannes Gäßler
|
76d66ee0be
CUDA: faster q2_K, q3_K MMQ + int8 tensor cores (#7921)
|
1 year ago |
|
Georgi Gerganov
|
66ef1ceedf
metal : utilize max shared memory for mul_mat_id (#7935)
|
1 year ago |
 Radoslav Gerganov
|
e65bbf606c
llama-bench : fix RPC indication (#7936)
|
1 year ago |
