潘其威(William)
|
eea67b7e13
|
Merge pull request #256 from PanQiWei/rocm_build_bug_fix
Rocm build bug fix
|
2023-08-13 17:14:40 +08:00 |
|
PanQiWei
|
8542b3dc9f
|
execute setup tools install before torch install
|
2023-08-13 16:49:21 +08:00 |
|
PanQiWei
|
79b697743f
|
disable free disk space action
|
2023-08-13 16:41:20 +08:00 |
|
PanQiWei
|
893fc5d7a3
|
release 0.4.1
|
2023-08-13 16:35:59 +08:00 |
|
PanQiWei
|
34b4ba451c
|
fix typo
|
2023-08-13 16:26:02 +08:00 |
|
潘其威(William)
|
1832685121
|
Merge pull request #243 from fxmarty/patch-act-order-exllama
Patch exllama QuantLinear to avoid modifying the state dict
|
2023-08-10 11:15:10 +08:00 |
|
Felix Marty
|
4af7ea619d
|
patch for transformers compatiblity
|
2023-08-09 14:23:59 +00:00 |
|
PanQiWei
|
6a277c87cf
|
fix syntax error
|
2023-08-09 19:44:29 +08:00 |
|
PanQiWei
|
d178ebd2fe
|
set branch to main
|
2023-08-09 19:39:05 +08:00 |
|
PanQiWei
|
9978d6e9f9
|
set branch to rocm_build_bug_fix
|
2023-08-09 19:37:05 +08:00 |
|
PanQiWei
|
aea761042d
|
fix only one python version used
|
2023-08-09 19:36:37 +08:00 |
|
PanQiWei
|
69cdfe80fd
|
fix syntax error
|
2023-08-09 18:05:30 +08:00 |
|
PanQiWei
|
44c7a1a184
|
make exllama_kernels compilation as optional
|
2023-08-09 17:42:22 +08:00 |
|
PanQiWei
|
e30bb69dee
|
revert to remove 3.11 support
|
2023-08-09 14:55:42 +08:00 |
|
PanQiWei
|
918842a083
|
Revert "remove 3.11 for now"
This reverts commit b5a7c813e3.
|
2023-08-09 14:51:11 +08:00 |
|
PanQiWei
|
c5acab3aec
|
Revert "remove upload sdist step"
This reverts commit 9baff43f6f.
|
2023-08-09 14:49:13 +08:00 |
|
PanQiWei
|
b5a7c813e3
|
remove 3.11 for now
|
2023-08-09 14:34:03 +08:00 |
|
PanQiWei
|
60ea23d464
|
fix py3.11 can't build
|
2023-08-09 14:05:44 +08:00 |
|
PanQiWei
|
115f004c5e
|
fix wrong index-url
|
2023-08-09 13:37:19 +08:00 |
|
PanQiWei
|
6d5ce1d386
|
temporarily disable rocm 5.5 and 5.6 support until pytorch 2.1.0 is officially released
|
2023-08-09 13:35:52 +08:00 |
|
PanQiWei
|
db9eabfc4b
|
add disable_exllama argument
|
2023-08-09 12:05:15 +08:00 |
|
PanQiWei
|
172deae049
|
expose disable_exllama argument
|
2023-08-09 12:03:31 +08:00 |
|
PanQiWei
|
86a3d4a094
|
release 0.4.0
|
2023-08-09 11:54:31 +08:00 |
|
潘其威(William)
|
3fb7d1ed1c
|
Merge pull request #240 from PanQiWei/support-qwen
support qwen
|
2023-08-08 19:24:24 +08:00 |
|
qwopqwop200
|
fe244503e0
|
add ","
|
2023-08-08 19:57:23 +09:00 |
|
qwopqwop200
|
d22f89c524
|
support qwen
|
2023-08-08 19:27:43 +09:00 |
|
潘其威(William)
|
5981f15dc3
|
Merge pull request #236 from PanQiWei/suppprt-static_groups
Suppprt static groups and fix bug
|
2023-08-08 14:29:39 +08:00 |
|
qwopqwop200
|
dc5541e78a
|
static groups default value change
|
2023-08-08 14:11:39 +09:00 |
|
qwopqwop200
|
2f48780165
|
fix bug disable exlllama
|
2023-08-07 16:28:30 +09:00 |
|
qwopqwop200
|
25972d65bf
|
support static_groups and fix bug
|
2023-08-07 16:27:48 +09:00 |
|
qwopqwop200
|
6233afce3b
|
support static_groups
|
2023-08-07 16:25:44 +09:00 |
|
PanQiWei
|
d427489911
|
update README
|
2023-08-06 20:03:33 +08:00 |
|
潘其威(William)
|
9e2741c99d
|
Merge pull request #219 from fxmarty/exllama-q4-kernel
Add exllama q4 kernel
|
2023-08-06 19:53:40 +08:00 |
|
fxmarty
|
71f23268eb
|
Merge pull request #1 from qwopqwop200/exllama-q4-kernel
Exllama q4 kernel
|
2023-08-05 00:15:22 +09:00 |
|
Felix Marty
|
c203a85dee
|
fix
|
2023-08-04 15:00:12 +00:00 |
|
Felix Marty
|
d0608b09db
|
rocm support
|
2023-08-04 13:38:02 +00:00 |
|
Félix Marty
|
4fb3e20c5e
|
Merge branch 'main' into exllama-q4-kernel
|
2023-08-04 15:13:34 +02:00 |
|
潘其威(William)
|
5d8fa85029
|
Merge pull request #226 from LeiWang1999/fix/general_attr
Register quant params in GeneralQuantLinear for friendly post process.
|
2023-08-04 18:42:54 +08:00 |
|
潘其威(William)
|
45152b7add
|
Merge pull request #220 from fxmarty/fix-revison-loading
Fix revision used to load the quantization config
|
2023-08-04 18:25:22 +08:00 |
|
潘其威(William)
|
63da0cd00a
|
Merge pull request #214 from fxmarty/rocm-support
Add RoCm support
|
2023-08-04 18:24:15 +08:00 |
|
潘其威(William)
|
e6790ba2cb
|
Update README.md
|
2023-08-04 18:16:55 +08:00 |
|
qwopqwop200
|
79ab5076c7
|
revert fused_llama_attn.py
|
2023-08-04 18:19:54 +09:00 |
|
qwopqwop200
|
068210d0b7
|
exllama support flash attention
|
2023-08-03 16:30:16 +09:00 |
|
qwopqwop200
|
7a7df5655a
|
support group query attention
|
2023-08-03 16:08:49 +09:00 |
|
leiwang1999
|
a0de5c2c51
|
regist buffer of general quant linear
|
2023-08-03 05:15:09 +00:00 |
|
qwopqwop200
|
3fc097dcd8
|
change pcak func support only 4 bit
|
2023-08-01 20:01:45 +09:00 |
|
qwopqwop200
|
a1fd81c72d
|
if training disable exllama
|
2023-08-01 12:29:58 +09:00 |
|
qwopqwop200
|
a60c9a8552
|
add pack fun
|
2023-08-01 12:22:41 +09:00 |
|
Felix Marty
|
7ce182888c
|
fix atol
|
2023-07-31 16:46:15 +00:00 |
|
Felix Marty
|
339c57a902
|
fix
|
2023-07-31 15:57:44 +00:00 |
|