Ying Sheng
|
37963394aa
|
[Feature] Support LoRA path renaming and add LoRA serving benchmarks (#1433)
|
2024-09-15 12:46:04 -07:00 |
|
Lianmin Zheng
|
e4d68afcf0
|
[Minor] Many cleanup (#1357)
|
2024-09-09 04:14:11 -07:00 |
|
Kai-Hsun Chen
|
c9b75917d5
|
[server] Passing model_override_args to launch_server via the CLI. (#1298)
Signed-off-by: Kai-Hsun Chen <kaihsun@anyscale.com>
|
2024-09-09 02:14:25 -07:00 |
|
Yineng Zhang
|
62f15eea5a
|
docs: add conclusion (#1340)
|
2024-09-06 04:25:14 +10:00 |
|
Yineng Zhang
|
79794af52d
|
docs: highlight ttft itl and throughput (#1337)
|
2024-09-06 00:00:06 +10:00 |
|
Yineng Zhang
|
3494b32c3a
|
docs: update README (#1336)
|
2024-09-05 23:39:44 +10:00 |
|
Lianmin Zheng
|
57d0bd91ec
|
Improve benchmark (#1140)
|
2024-08-17 17:43:23 -07:00 |
|
Lianmin Zheng
|
5a261bd055
|
Fix the deadlock in multi-node tp (#1122)
|
2024-08-16 01:39:24 -07:00 |
|
Lianmin Zheng
|
326df4bab2
|
Use a single workspace for flashinfer (#1077)
|
2024-08-14 19:25:37 -07:00 |
|
Yineng Zhang
|
1c2b5f5240
|
docs: update nsys usage (#1103)
|
2024-08-15 01:39:15 +08:00 |
|
Liangsheng Yin
|
a34dd86a7d
|
Use dtype to control generate (#1082)
Co-authored-by: zhyncs <me@zhyncs.com>
|
2024-08-14 15:58:07 +00:00 |
|
Lianmin Zheng
|
a59636bb5e
|
Update grok 1 model (#1095)
|
2024-08-14 04:40:44 -07:00 |
|
Meng, Peng
|
41bb1ab10d
|
fix nsys cannot profile cuda kernel (#957)
|
2024-08-07 11:51:21 +08:00 |
|
Ke Bao
|
e1eae1fd15
|
Support MLA for DeepSeek-V2 with Triton - step 1 (#905)
|
2024-08-05 03:40:33 +10:00 |
|
Yineng Zhang
|
1edd4e07d6
|
chore: bump v0.2.7 (#830)
|
2024-07-30 20:41:10 +10:00 |
|
Yineng Zhang
|
a50c8a14b3
|
fix: use v0.2.5 for benchmark (#814)
|
2024-07-30 12:40:35 +10:00 |
|
Ying Sheng
|
db6089e6f3
|
Revert "Organize public APIs" (#815)
|
2024-07-29 19:40:28 -07:00 |
|
Liangsheng Yin
|
c8e9fed87a
|
Organize public APIs (#809)
|
2024-07-29 15:34:16 -07:00 |
|
Yineng Zhang
|
768e05d08f
|
fix benchmark (#743)
Co-authored-by: hnyls2002 <hnyls2002@gmail.com>
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
|
2024-07-26 21:26:13 +10:00 |
|
Yineng Zhang
|
fded67441d
|
misc: update bulid instruction (#724)
|
2024-07-25 17:08:11 +10:00 |
|
Yineng Zhang
|
97e0f7d250
|
docs: update comment (#721)
|
2024-07-25 10:51:18 +10:00 |
|
Ying Sheng
|
30d8e130e7
|
Improve benchmark scripts (#717)
|
2024-07-24 14:44:14 -07:00 |
|
Ying Sheng
|
08a3bd19cc
|
docs: update doc (#716)
|
2024-07-24 20:44:03 +00:00 |
|
Yineng Zhang
|
321a963b01
|
misc: update doc (#715)
|
2024-07-24 13:05:46 -07:00 |
|
Yineng Zhang
|
2d3ae4e125
|
docs: update doc (#713)
|
2024-07-25 00:03:17 +10:00 |
|
Yineng Zhang
|
75f4ccb7dd
|
docs: update README (#712)
|
2024-07-24 23:33:28 +10:00 |
|
Lianmin Zheng
|
490a1f39dd
|
Fix cuda graph with flashinfer (#675)
|
2024-07-20 02:43:55 -07:00 |
|
zhyncs
|
2e341cd493
|
misc: add pre-commit config (#637)
|
2024-07-17 11:55:39 -07:00 |
|
Lianmin Zheng
|
41d1f67704
|
Fix flush cache (#627)
|
2024-07-15 20:44:04 -07:00 |
|
Ying Sheng
|
6a2941f4d0
|
Improve tensor parallel performance (#625)
Co-authored-by: Mingyi <wisclmy0611@gmail.com>
|
2024-07-15 07:10:51 -07:00 |
|
Mingyi
|
5ac8b80677
|
Simplify mem state (#623)
|
2024-07-15 02:01:09 -07:00 |
|
Ying Sheng
|
bae9541e4c
|
Update benchmark script (#621)
|
2024-07-14 21:38:53 +00:00 |
|
Liangsheng Yin
|
564a898ad9
|
Optimize mem indices mangement (#619)
|
2024-07-13 23:39:37 -07:00 |
|
Lianmin Zheng
|
0feca02dd9
|
Improve benchmark scripts (#615)
|
2024-07-13 15:59:04 -07:00 |
|
Lianmin Zheng
|
65c6577696
|
Improve benchmark scripts & fix llava (#613)
|
2024-07-13 15:00:26 -07:00 |
|
Lianmin Zheng
|
665815969a
|
Enable cuda graph by default (#612)
|
2024-07-13 05:29:46 -07:00 |
|
Liangsheng Yin
|
f25b76c02a
|
add LogitsMetadata (#604)
|
2024-07-08 17:46:55 -07:00 |
|
Ying Sheng
|
dc1b8bcfaa
|
Format (#593)
|
2024-07-05 10:06:17 -07:00 |
|
sglang
|
11616fc6bd
|
Minor fix in compiler & format (#545)
|
2024-06-29 23:42:14 -07:00 |
|
Lianmin Zheng
|
945aa9beb2
|
Update readme (#568)
|
2024-06-27 11:37:49 -07:00 |
|
Lianmin Zheng
|
2e6e62e156
|
Increase the number of thread limitation for tp worker managers. (#567)
|
2024-06-26 09:33:45 -07:00 |
|
Lianmin Zheng
|
a385ee27bd
|
Warmup cublas (#566)
|
2024-06-25 12:46:00 -07:00 |
|
Liangsheng Yin
|
92cb93f390
|
Fix latency benchmark (#557)
|
2024-06-22 15:11:04 +08:00 |
|
Ying Sheng
|
09593e9bc9
|
Multi-node Tensor Parallelism (#550)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
|
2024-06-17 20:41:24 -07:00 |
|
Liangsheng Yin
|
40e53d65cb
|
Add disk cache for loading ShareGPT dataset. (#542)
|
2024-06-13 16:37:12 +08:00 |
|
Ying Sheng
|
fb9296f0ed
|
Higher priority for user input of max_prefill_tokens & format (#540)
|
2024-06-12 21:48:40 -07:00 |
|
Ying Sheng
|
1374334d38
|
Fix dependency & crash issues (#539)
|
2024-06-12 21:23:19 -07:00 |
|
Lianmin Zheng
|
3bc01ac137
|
[Minor] improve code style
|
2024-06-03 18:11:34 -07:00 |
|
Lianmin Zheng
|
09de730dee
|
Improve benchmark scripts & add more models (#484)
|
2024-05-27 14:13:26 -07:00 |
|
Lianmin Zheng
|
55c1643627
|
Improve benchmark scripts & rename some scripts (#477)
|
2024-05-26 12:51:45 -07:00 |
|