Simon Mo
|
cf68f9893b
|
Merge pull request #8 from tjtanaa/2024-10-23-vllm-serving-amd-amend-tj
[FIX] Amend benchmark command and model data type
|
2024-10-30 09:28:57 -07:00 |
tunjiantan
|
9769c02a65
|
amend data type
Signed-off-by: tunjiantan <tunjian.tan@embeddedllm.com>
|
2024-10-30 16:24:17 +00:00 |
|
tunjiantan
|
cc0466fe0f
|
amend benchmark command
Signed-off-by: tunjiantan <tunjian.tan@embeddedllm.com>
|
2024-10-30 16:24:17 +00:00 |
|
Simon Mo
|
dc147caa3f
|
Merge pull request #7 from tjtanaa/2024-10-23-vllm-serving-amd-spelling-fix-tj
[Bug] [Spelling] Fix spell spelling
|
2024-10-29 17:31:28 -07:00 |
|
tunjiantan
|
b254fde054
|
fix spell check
Signed-off-by: tunjiantan <tunjian.tan@embeddedllm.com>
|
2024-10-29 23:46:56 +00:00 |
|
simon-mo
|
8a000df791
|
add favicon
|
2024-10-29 11:28:55 -07:00 |
|
simon-mo
|
78b72d36e3
|
amd post edits
|
2024-10-29 11:26:03 -07:00 |
|
Simon Mo
|
cf0725059e
|
Merge pull request #5 from tjtanaa/vllm-serving-amd-blogpost-tj
[Blog Post] Serving LLMs on AMD MI300X: Best Practices
|
2024-10-23 10:27:20 -07:00 |
|
tunjiantan
|
aa86e74ea6
|
add 2024-10-23-vllm-serving-amd blog post
Signed-off-by: tunjiantan <tunjian.tan@embeddedllm.com>
|
2024-10-23 10:29:32 +00:00 |
LiuXiaoxuanPKU
|
5c940c665f
|
minor
|
2024-10-22 11:39:37 -07:00 |
|
LiuXiaoxuanPKU
|
c02becf2bd
|
minor
|
2024-10-22 11:20:25 -07:00 |
|
LiuXiaoxuanPKU
|
0a12f21577
|
minor
|
2024-10-22 11:17:53 -07:00 |
|
LiuXiaoxuanPKU
|
98a2b59850
|
edit
|
2024-10-22 11:12:11 -07:00 |
|
simon-mo
|
a9bae7a33e
|
spec decode edits
|
2024-10-18 10:49:39 -07:00 |
|
simon-mo
|
a26b36612f
|
Add spec decode blog
|
2024-10-17 13:30:16 -07:00 |
Zhuohan Li
|
ba30fb1b28
|
add limitation
|
2024-09-06 09:58:22 -07:00 |
|
Zhuohan Li
|
0dd37adf40
|
add missing paragraph
|
2024-09-05 11:36:55 -07:00 |
|
simon-mo
|
711ec962d4
|
Revert "try twitter header image"
This reverts commit 6fc0369073.
|
2024-09-05 10:20:35 -07:00 |
|
simon-mo
|
53fa45b220
|
Revert "fix"
This reverts commit 13d83e3636.
|
2024-09-05 10:20:28 -07:00 |
|
simon-mo
|
13d83e3636
|
fix
|
2024-09-05 09:58:27 -07:00 |
|
simon-mo
|
6fc0369073
|
try twitter header image
|
2024-09-05 09:56:33 -07:00 |
|
Zhuohan Li
|
12ae2a2d7a
|
small fix
|
2024-09-05 09:54:01 -07:00 |
|
Zhuohan Li
|
fadcbcc3cd
|
change acknowledgement
|
2024-09-05 09:48:33 -07:00 |
|
Zhuohan Li
|
67d2c32341
|
fix minor issues
|
2024-09-05 09:44:03 -07:00 |
|
Zhuohan Li
|
1b304fef5c
|
minor fixes
|
2024-09-05 00:18:44 -07:00 |
|
Zhuohan Li
|
5aa2180327
|
change will's name
|
2024-09-05 00:08:57 -07:00 |
|
Zhuohan Li
|
73405ded17
|
remove the in the author
|
2024-09-05 00:07:06 -07:00 |
|
Zhuohan Li
|
31cb4a5733
|
Change date
|
2024-09-05 00:03:11 -07:00 |
|
Zhuohan Li
|
321025b5d7
|
Add some hard-coded change in html to markdown
|
2024-09-05 00:02:30 -07:00 |
|
Zhuohan Li
|
ce90fa1339
|
Add v0.6.0 perf blog and also modify readme on how to publish a blogpost
|
2024-09-04 23:57:30 -07:00 |
|
simon-mo
|
99c42c3c05
|
update snowflake to llama3.1 post
|
2024-08-07 14:27:00 -07:00 |
|
simon-mo
|
d39c04f6f2
|
Add snowflake to llama3.1 post
|
2024-08-07 13:57:47 -07:00 |
|
simon-mo
|
bd0a2e74c1
|
update figure
|
2024-07-25 15:14:57 -07:00 |
|
simon-mo
|
90a64dddc0
|
typo
|
2024-07-25 15:03:48 -07:00 |
|
simon-mo
|
d85b0ef5b5
|
backport llama changes
|
2024-07-25 14:56:53 -07:00 |
|
simon-mo
|
9227cfd6d5
|
update lfai
|
2024-07-25 14:56:21 -07:00 |
|
simon-mo
|
33d16cb301
|
initial draft for lfai post
|
2024-07-25 14:44:46 -07:00 |
|
Zhuohan Li
|
f11c9ef0d2
|
Add Llama 3.1 blogpost (new files)
|
2024-07-25 13:35:26 -07:00 |
|
Zhuohan Li
|
a833fde072
|
add llama3.1 blogpost
|
2024-07-22 22:16:08 -07:00 |
|
Zhuohan Li
|
c7a068ba20
|
fix github link
|
2023-11-14 16:44:56 -08:00 |
Woosuk Kwon
|
d9970f9003
|
model & hardward
|
2023-11-14 23:11:49 +00:00 |
|
Woosuk Kwon
|
98626b451c
|
Merge pull request #3 from vllm-project/fastgen
FastGen
|
2023-11-14 15:00:16 -08:00 |
|
Woosuk Kwon
|
1d9d5b235d
|
FastGen
|
2023-11-14 22:42:57 +00:00 |
|
Zhuohan Li
|
73685a63a9
|
Merge pull request #2 from vllm-project/bold
Bold
|
2023-11-14 14:32:29 -08:00 |
|
Woosuk Kwon
|
f67078d283
|
bold
|
2023-11-14 22:29:29 +00:00 |
|
Woosuk Kwon
|
600dace4c4
|
Polish DeepSpeed blog post (#1)
|
2023-11-14 13:50:21 -08:00 |
|
Woosuk Kwon
|
783c7628b2
|
Update _posts/2023-11-14-notes-vllm-vs-deepspeed.md
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
|
2023-11-14 12:45:39 -08:00 |
|
Woosuk Kwon
|
5232941cfe
|
Update _posts/2023-11-14-notes-vllm-vs-deepspeed.md
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
|
2023-11-14 12:45:32 -08:00 |
|
Woosuk Kwon
|
a0f139a454
|
Update _posts/2023-11-14-notes-vllm-vs-deepspeed.md
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
|
2023-11-14 12:45:25 -08:00 |
|
Woosuk Kwon
|
ba9eb7994f
|
Update _posts/2023-11-14-notes-vllm-vs-deepspeed.md
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
|
2023-11-14 12:45:17 -08:00 |