Zack Li
df5841b6b8
Merge pull request #13 from NexaAI/weili/master-release
...
add omni-vlm-v2 implementations( C++ & python）
2024-11-07 00:48:21 -08:00
李为
3dfac7817f
add returned string type (const char*) for nexa-omni-audio
2024-11-07 16:13:53 +08:00
Zack Li
20b9f02cee
Merge pull request #12 from NexaAI/weili/master-release
...
add returned string type (const char*) for nexa-omni-audio
2024-11-06 19:28:46 -08:00
李为
5edadffd88
add returned string type (const char*) for nexa-omni-audio
2024-11-07 11:19:50 +08:00
Zack Li
6a4cf0b983
Merge pull request #11 from NexaAI/weili/master-release
...
add returned string (const char*) for qwen2 audio
2024-11-05 23:27:47 -08:00
李为
b24a409e22
add returned string (const char*) for qwen2 audio
2024-11-06 15:24:26 +08:00
Zack Li
5574bda471
Merge pull request #10 from NexaAI/weili/master-release
...
add returned string (pure c const char* type) for omni-vlm inference api
2024-11-05 19:41:03 -08:00
李为
22da7bc379
add returned string (pure c const char* type) for omni-vlm inference api
2024-11-06 11:20:36 +08:00
Zack Li
983b4625ef
Merge pull request #8 from NexaAI/weili/master-release
...
add omni-vlm examples (C++ & python)
2024-11-04 22:39:36 -08:00
Zack Li
91b3cafbb5
Merge pull request #6 from NexaAI/master-release-audio-lm
...
Remove C++20 coding and suport Microsoft Visual Studio Compilation
2024-11-04 21:59:26 -08:00
Zack Zhiyuan Li
05853eb861
remove C++20 syntax
2024-11-04 23:03:49 +00:00
Zack Zhiyuan Li
d42e0371f8
remove C++20 style
2024-11-04 22:50:33 +00:00
Zack Zhiyuan Li
1419681089
disable <cxxabi.h> for MSC_VER
2024-11-04 05:45:52 +00:00
Zack Zhiyuan Li
6f1ed6e5cb
Adding #include <io.h> & <fcntl.h>
2024-11-04 04:54:51 +00:00
Zack Zhiyuan Li
a4747b2edb
fix error on windows qwen2-audio/whisper.cpp:9935:38: error: '_O_BINARY' was not declared in this scope
2024-11-04 04:40:41 +00:00
Zack Zhiyuan Li
995baefeed
Disable cxxabi.h dependency on Windows
2024-11-04 03:48:20 +00:00
李为
d277c674ae
add omni-vlm examples (C++ & python)
2024-11-04 09:56:33 +08:00
Zack Zhiyuan Li
4bdc70aaac
update to C++17 for compilation
2024-11-03 22:07:07 +00:00
Zack Zhiyuan Li
9e67ef75b4
remove uneccesary build and rename shared lib
2024-11-03 21:29:09 +00:00
Zack Zhiyuan Li
f0d1c4fa1c
enable qwen2-audio work E2E
2024-11-03 18:33:32 +00:00
Zack Zhiyuan Li
c7b912bdca
support omni-audio
2024-11-03 17:58:08 +00:00
Zack Zhiyuan Li
4a29bca867
update vulkan target name
2024-10-23 20:54:39 +00:00
Zack Li
3a3552632a
update README after renaming GGML
2024-09-10 20:53:14 +00:00
Zack Li
5f81588780
support ggml
2024-09-10 20:50:54 +00:00
Georgi Gerganov
1d1ccce676
flake.lock: Update ( #9162 )
...
Flake lock file updates:
• Updated input 'nixpkgs':
'github:NixOS/nixpkgs/c3aa7b8938b17aebd2deecf7be0636000d62a2b9?narHash=sha256-med8%2B5DSWa2UnOqtdICndjDAEjxr5D7zaIiK4pn0Q7c%3D' (2024-08-14)
→ 'github:NixOS/nixpkgs/c374d94f1536013ca8e92341b540eba4c22f9c62?narHash=sha256-Z/ELQhrSd7bMzTO8r7NZgi9g5emh%2BaRKoCdaAv5fiO0%3D' (2024-08-21)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-08-28 21:28:14 -07:00
slaren
9fe94ccac9
docker : build images only once ( #9225 )
2024-08-28 17:28:00 +02:00
slaren
66b039a501
docker : update CUDA images ( #9213 )
2024-08-28 13:20:36 +02:00
Georgi Gerganov
20f1789dfb
vulkan : fix build ( #0 )
...
ggml-ci
2024-08-27 22:41:27 +03:00
Georgi Gerganov
231cff5f6f
sync : ggml
2024-08-27 22:41:27 +03:00
Xie Yanbo
3246fe84d7
Fix minicpm example directory ( #9111 )
2024-08-27 14:33:08 +02:00
compilade
78eb487bb0
llama : fix qs.n_attention_wv for DeepSeek-V2 ( #9156 )
2024-08-27 13:09:23 +03:00
Xuan Son Nguyen
a77feb5d71
server : add some missing env variables ( #9116 )
...
* server : add some missing env variables
* add LLAMA_ARG_HOST to server dockerfile
* also add LLAMA_ARG_CONT_BATCHING
2024-08-27 11:07:01 +02:00
CausalLM
2e59d61c1b
llama : fix ChatGLM4 wrong shape ( #9194 )
...
This should fix THUDM/glm-4-9b-chat-1m and CausalLM/miniG
2024-08-27 09:58:22 +03:00
Carsten Kragelund Jørgensen
75e1dbbaab
llama : fix llama3.1 rope_freqs not respecting custom head_dim ( #9141 )
...
* fix: llama3.1 rope_freqs not respecting custom head_dim
* fix: use potential head_dim for Exaone
2024-08-27 09:53:40 +03:00
arch-btw
ad76569f8e
common : Update stb_image.h to latest version ( #9161 )
...
* Update stb_image.h to latest version
Fixes https://github.com/ggerganov/llama.cpp/issues/7431
* Update .ecrc
2024-08-27 08:58:50 +03:00
slaren
7d787ed96c
ggml : do not crash when quantizing q4_x_x with an imatrix ( #9192 )
2024-08-26 19:44:43 +02:00
Georgi Gerganov
06658ad7c3
metal : separate scale and mask from QKT in FA kernel ( #9189 )
...
* metal : separate scale and mask from QKT in FA kernel
* metal : ne01 check no longer necessary
* metal : keep data in local memory
2024-08-26 18:31:02 +03:00
Georgi Gerganov
fc18425b6a
ggml : add SSM Metal kernels ( #8546 )
...
* ggml : add ggml_ssm_conv metal impl
* ggml : add ssm_scan metal impl
ggml-ci
2024-08-26 17:55:36 +03:00
Georgi Gerganov
879275ac98
tests : fix compile warnings for unreachable code ( #9185 )
...
ggml-ci
2024-08-26 16:30:25 +03:00
Georgi Gerganov
7a3df798fc
ci : add VULKAN support to ggml-ci ( #9055 )
2024-08-26 12:19:39 +03:00
Georgi Gerganov
e5edb210cd
server : update deps ( #9183 )
2024-08-26 12:16:57 +03:00
slaren
0c41e03ceb
metal : gemma2 flash attention support ( #9159 )
2024-08-26 11:08:59 +02:00
slaren
f12ceaca0c
ggml-ci : try to improve build time ( #9160 )
2024-08-26 11:03:30 +02:00
Justine Tunney
436787f170
llama : fix time complexity of string replacement ( #9163 )
...
This change fixes a bug where replacing text in a very long string could
cause llama.cpp to hang indefinitely. This is because the algorithm used
was quadratic, due to memmove() when s.replace() is called in a loop. It
seems most search results and LLM responses actually provide the O(n**2)
algorithm, which is a great tragedy. Using a builder string fixes things
2024-08-26 09:09:53 +03:00
Herman Semenov
93bc3839f9
common: fixed not working find argument --n-gpu-layers-draft ( #9175 )
2024-08-26 00:54:37 +02:00
Johannes Gäßler
f91fc5639b
CUDA: fix Gemma 2 numerical issues for FA ( #9166 )
2024-08-25 22:11:48 +02:00
Johannes Gäßler
e11bd856d5
CPU/CUDA: Gemma 2 FlashAttention support ( #8542 )
...
* CPU/CUDA: Gemma 2 FlashAttention support
* apply logit_softcap to scale in kernel
* disable logit softcapping tests on Metal
* remove metal check
2024-08-24 21:34:59 +02:00
João Dinis Ferreira
8f824ffe8e
quantize : fix typo in usage help of quantize.cpp ( #9145 )
2024-08-24 09:22:45 +03:00
Xuan Son Nguyen
3ba780e2a8
lora : fix llama conversion script with ROPE_FREQS ( #9117 )
2024-08-23 12:58:53 +02:00
piDack
a07c32ea54
llama : use F32 precision in GLM4 attention and no FA ( #9130 )
2024-08-23 10:27:17 +03:00
