GithubStar/ktransformers
1
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-10-28 21:51:46 +08:00
Code Issues Packages Projects Releases Wiki Activity
638 Commits 73 Branches 44 Tags
797dac7e317ce1e81126bc7bc84300a32d050778
Commit Graph
638 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
ErvinXie 797dac7e31 Merge pull request #1109 from aubreyli/libxxhash-fPIC 
xxHash: fix link error due to non-position-independent code
 2025-04-13 14:15:31 +08:00
ZiWei Yuan 77956822ce Merge pull request #1116 from ikawrakow/ik/add_copyright 
Add missing references to ik_llama.cpp
 2025-04-13 11:53:12 +08:00
Iwan Kawrakow 99a247e167 Spelling 2025-04-11 10:15:42 +03:00
Iwan Kawrakow c46b0c59d0 Add missing references to ik_llama.cpp 2025-04-11 09:39:57 +03:00
Aubrey Li 63ca2fa84d xxHash: fix link error due to non-position-independent code 
Add PROPERTIES POSITION_INDEPENDENT_CODE option to fix the
following error:

/usr/bin/ld: ../../third_party/xxHash/libxxhash.a(xxhash.c.o):
relocation R_X86_64_32S against `.rodata' can not be used when
making a shared object; recompile with -fPIC

Trying to link a non-PIC static library libxxhash.a into a
.so shared library, which is not allowed. The object file
xxhash.c.o must be recompiled with explicit -fPIC support.
 2025-04-10 21:50:23 +08:00
Atream 35ba63e259 Merge pull request #1103 from kvcache-ai/Atream-patch-6 
Create SECURITY.md
 2025-04-09 19:50:57 +08:00
Atream 5f8cdc7640 Create SECURITY.md 2025-04-09 19:50:38 +08:00
Atream 92a67ab549 Merge pull request #1101 from kvcache-ai/Atream-patch-5 
Update llama4.md
 2025-04-09 19:23:46 +08:00
Atream 98dbdcd66c Update llama4.md 2025-04-09 19:23:35 +08:00
Atream 9fad782c1a Merge pull request #1100 from kvcache-ai/Atream-patch-4 
Update llama4.md
 2025-04-09 19:10:03 +08:00
Atream 346d202297 Update llama4.md 2025-04-09 19:09:44 +08:00
Atream a46c43b2db Merge pull request #1099 from kvcache-ai/Atream-patch-3 
Update llama4.md
 2025-04-09 18:01:46 +08:00
Atream d1fcb208cc Update llama4.md 2025-04-09 18:01:13 +08:00
Atream 0774fe4d62 Merge pull request #1098 from kvcache-ai/Atream-patch-2 
Update llama4.md
 2025-04-09 17:58:44 +08:00
Atream ed2b971e02 Update llama4.md 2025-04-09 17:57:37 +08:00
Jianwei Dong c689b23364 Merge pull request #1097 from kvcache-ai/update-llama4-tutorial 
update llama4 tutorial
 2025-04-09 17:40:58 +08:00
djw 26798500bd update llama4 tutorial 2025-04-09 09:40:08 +00:00
Jianwei Dong 1e0be68e51 Merge pull request #1096 from kvcache-ai/update-llama4-tutorial 
update llama4 tutorial
 2025-04-09 17:37:33 +08:00
djw f73b4ca706 update llama4 tutorial 2025-04-09 09:36:30 +00:00
Jianwei Dong 2de96a1f05 Merge pull request #1095 from kvcache-ai/update-llama4-tutorial 
update llama4 tutorial
 2025-04-09 17:35:14 +08:00
djw ecc3028c13 update llama4 tutorial 2025-04-09 09:34:04 +00:00
Azure a74a58d864 Merge pull request #1091 from aubreyli/add_g++ 
balance_serve: Add g++ to compiler list
 2025-04-09 14:40:30 +08:00
Aubrey Li 45d20fa87b balance_serve: Add g++ to compiler list 
In some OS distributions, g++ exists in the following form:

  # ls -l /usr/bin/g++*
  -rwxr-xr-x 4 root root 985784 Dec  9 12:51 /usr/bin/g++

So make sure to add g++ to the compiler list as well.
 2025-04-09 11:25:35 +08:00
Atream 9037bf30d5 Merge pull request #1090 from kvcache-ai/Atream-patch-1 
Update attention.py
 2025-04-09 10:54:37 +08:00
Atream 3b9e16cec7 Update attention.py 2025-04-09 10:54:00 +08:00
wang jiahao 94476ce5cc Merge pull request #1085 from kvcache-ai/qiyuxinlin-patch-5 
Update balance-serve.md
 2025-04-08 19:19:37 +08:00
wang jiahao 23ceb1c049 Update balance-serve.md 2025-04-08 19:19:00 +08:00
wang jiahao 41ce92bb22 Merge pull request #1084 from kvcache-ai/fix-config 
format kvc2, delete quant_configs, move model_configs to ~/.ktransfor…
 2025-04-08 19:14:07 +08:00
qiyuxinlin 64de784328 format kvc2, delete quant_configs, move model_configs to ~/.ktransformers 2025-04-08 10:06:07 +00:00
Atream 10fd2e281f Merge pull request #1079 from kvcache-ai/fix-compile 
fix compile, add abi check to setup.py
 2025-04-08 14:36:31 +08:00
Atream 9dd24ecd72 fix compile, add abi check to setup.py 2025-04-08 06:18:30 +00:00
wang jiahao f4ae7c85ed Merge pull request #1069 from kvcache-ai/qiyuxinlin-patch-4 
Update balance-serve.md
 2025-04-07 19:20:00 +08:00
wang jiahao 2fcdbee769 Update balance-serve.md 2025-04-07 19:19:49 +08:00
Azure 77c6cc82ac Merge pull request #1063 from aubreyli/KLinearCPUInfer.forward-fix 
Fix TypeError when invoke KLinearCPUInfer.forward()
 2025-04-07 15:10:46 +08:00
wang jiahao 6463070b16 Merge pull request #1064 from kvcache-ai/fix-temperature 
fix temperature=0, flashinfer sample error
 2025-04-07 12:32:28 +08:00
dongjw ec03bcbd7f fix temperature=0, flashinfer sample error 2025-04-07 12:30:47 +08:00
Atream aac0c91d02 Merge pull request #1060 from kvcache-ai/fix-compile 
Fix compile
 2025-04-07 12:10:31 +08:00
Aubrey Li 12a4c631df Fix TypeError when invoke KLinearCPUInfer.forward() 
Fix the following error:

  File "/home/aubrey/work/ktransformers/ktransformers/operators/linear.py", line 825, in forward
    y = self.generate_linear.forward(x, bsz_tensor)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: KLinearCPUInfer.forward() takes 2 positional arguments but 3 were given
 2025-04-07 12:03:35 +08:00
Atream fa87c1aeea Update CMakeLists.txt 2025-04-07 10:32:30 +08:00
Atream ad2009425c Update CMakeLists.txt 2025-04-07 10:32:12 +08:00
Atream f53d5aa979 Create CMakeLists.txt 2025-04-07 10:30:55 +08:00
wang jiahao 6ca743ed7a Merge pull request #1049 from kvcache-ai/qiyuxinlin-patch-3 
Update balance-serve.md
 2025-04-05 11:49:16 +08:00
wang jiahao 6cbe044aae Update balance-serve.md 2025-04-05 11:49:05 +08:00
wang jiahao 8a1313ca4e Merge pull request #1044 from 255doesnotexist/patch-1 
📝 Docs: Clarify CMake version requirement for CUDA dialects
 2025-04-04 23:45:03 +08:00
255 578d3d9d09 📝 Docs: Clarify CMake version requirement for CUDA dialects 
Adds a note explaining that default CMake versions on systems like
Ubuntu 22.04 LTS might not support newer CUDA dialects (e.g., CUDA 20),
leading to specific build errors.

Recommends installing a newer CMake via the Kitware APT repository
as a resolution. This helps users troubleshoot errors like:
"Target ... requires the language dialect 'CUDA20', but CMake does not know the compile flags..."
 2025-04-04 20:11:59 +08:00
ZiWei Yuan 6617549de0 Merge pull request #1043 from kvcache-ai/KMSorSMS-patch-2 
🔖 release v0.2.4post1
v0.2.4post1 		2025-04-04 16:02:43 +08:00
ZiWei Yuan a5608dcb80 🔖 release v0.2.4post1 2025-04-04 16:01:25 +08:00
wang jiahao af36075bda Merge pull request #1042 from kvcache-ai/v0.2.4-fix 
Fix bug with non-base-multiple chunk_size, update test examples, and …
 2025-04-04 15:43:48 +08:00
dongjw be84d04253 Fix bug with non-base-multiple chunk_size, update test examples, and resolve issue with writing model_config. Hugging Face URL input is still unsupported. 2025-04-04 15:41:07 +08:00
ZiWei Yuan 64e6aa026a Merge pull request #1034 from kvcache-ai/patch_config 
🔧 update config.yaml setting default config
 2025-04-03 19:57:04 +08:00