Commits · 441cca773d28b2147d9fd14c6e699f29fe9754e7 · change / sglang

03 Jul, 2024 1 commit
- support gptj style rope in llama · 441cca77
  Chen Xuechen Li authored Jul 03, 2024
  
  441cca77
02 Jul, 2024 1 commit
- [BugFix] gemma loading weights "lm_head.weight" key error (#577) · 95dc093b
  Daniel Hernandez Garcia authored Jul 02, 2024
  
  95dc093b
30 Jun, 2024 1 commit
- Minor fix in compiler & format (#545) · 11616fc6
  sglang authored Jun 29, 2024
  
  11616fc6
22 Jun, 2024 1 commit
- Add LlamaForClassification (#559) · 1fa15099
  Lianmin Zheng authored Jun 22, 2024
  
  1fa15099
13 Jun, 2024 1 commit
- Higher priority for user input of max_prefill_tokens & format (#540) · fb9296f0
  Ying Sheng authored Jun 12, 2024
  
  fb9296f0
12 Jun, 2024 1 commit
- Fix dependency (#538) · 94aead9e
  Lianmin Zheng authored Jun 12, 2024
  
  94aead9e
11 Jun, 2024 1 commit
- Add ChatGLM Model Support (#516) · a8c787d2
  Qubitium authored Jun 12, 2024
```
Co-authored-by: ZX <zx@lbx.dev>
```
  a8c787d2
07 Jun, 2024 2 commits
- remove redundant pad_input_ids function (#500) · 651a23ee
  Amos You authored Jun 07, 2024
  
  651a23ee
- Update vllm to v0.4.3 (#511) · bf3e271f
  Lianmin Zheng authored Jun 07, 2024
```
Co-authored-by: Qubitium <417764+Qubitium@users.noreply.github.com>
Co-authored-by: ZX <zx@lbx.dev>
```
  bf3e271f
28 May, 2024 1 commit

Support data parallelism (static) (#480) · 0463f7fb

Ying Sheng authored May 27, 2024


Co-authored-by: Ying Sheng <ying.sheng@databricks.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>

0463f7fb

27 May, 2024 1 commit
- Improve benchmark scripts & add more models (#484) · 09de730d
  Lianmin Zheng authored May 27, 2024
  
  09de730d
26 May, 2024 1 commit
- [Feat/Fix] Refactoring Llava models into single file (#475) · 2b605ab1
  Li Bo authored May 27, 2024
  
  2b605ab1
21 May, 2024 2 commits
- port fp8 mixtral (#460) · 0fafc560
  Lianmin Zheng authored May 21, 2024
  
  0fafc560
- Use model loader from vllm (#459) · 19d2135c
  Lianmin Zheng authored May 21, 2024
  
  19d2135c
14 May, 2024 2 commits
- Format code (#441) · 690d162d
  Liangsheng Yin authored May 14, 2024
  
  690d162d
- [Feat] Add llava qwen, llava mistral (#419) · 664287b2
  Kaichen Zhang - NTU authored May 14, 2024
```
Co-authored-by: Bo Li <drluodian@gmail.com>
```
  664287b2
13 May, 2024 1 commit
- support llava video (#426) · 0992d85f
  Yuanhan Zhang authored May 14, 2024
  
  0992d85f
11 May, 2024 1 commit
- Compat with latest VLLM 0.4.2 main + fork.number rename + Flashinfer 0.0.4 (#380) · 33b242df
  Qubitium authored May 12, 2024
```
Co-authored-by: ZX <zx@lbx.dev>
Co-authored-by: ZhouXingg <165115237+ZhouXingg@users.noreply.github.com>
```
  33b242df
23 Apr, 2024 1 commit
- Revert removing the unused imports (#385) · 150d7020
  Liangsheng Yin authored Apr 23, 2024
  
  150d7020
22 Apr, 2024 1 commit
- add `.isort.cfg` (#378) · 9acc6e35
  Liangsheng Yin authored Apr 22, 2024
  
  9acc6e35
16 Apr, 2024 2 commits
- Fix commandr import; format code · 65501a9c
  Lianmin Zheng authored Apr 16, 2024
  
  65501a9c
- support `command-r` (#369) · db611066
  ZhouXingg authored Apr 17, 2024
  
  db611066
01 Apr, 2024 1 commit
- fix gemma import error · b0890631
  Ying Sheng authored Apr 01, 2024
  
  b0890631
28 Mar, 2024 1 commit
- [model] DBRX-instruct support (#337) · 2af565b3
  Liangsheng Yin authored Mar 29, 2024
  
  2af565b3
22 Mar, 2024 1 commit
- Add StableLM model. (#301) · b57abe16
  Jani Monoses authored Mar 22, 2024
  
  b57abe16
11 Mar, 2024 4 commits
- Improve gemma and documentations (#278) · faba293a
  Lianmin Zheng authored Mar 11, 2024
  
  faba293a
- Gemma Support (#256) · 89885b31
  Liangsheng Yin authored Mar 11, 2024
  
  89885b31
- replace skip_embed with input_embeds (#222) · 64fe3115
  Geary.Z authored Mar 11, 2024
  
  64fe3115
- Fix qwen config (#261) · a7ace9c8
  Liangsheng Yin authored Mar 11, 2024
  
  a7ace9c8
11 Feb, 2024 1 commit
- Fix the chat template for llava-v1.6-34b & format code (#177) · c51020cf
  Lianmin Zheng authored Feb 11, 2024
  
  c51020cf
06 Feb, 2024 2 commits
- Format code & move functions (#155) · 23f05005
  Lianmin Zheng authored Feb 06, 2024
  
  23f05005
- Add gptq quantization model support (#141) · 3ae78a09
  Arcmoon authored Feb 07, 2024
  
  3ae78a09
01 Feb, 2024 1 commit
- Yi-VL Model (#112) · 86442530
  Christopher Chou authored Feb 01, 2024
  
  86442530
31 Jan, 2024 1 commit
- Fix model loading & format code (#125) · ad82bac6
  Lianmin Zheng authored Jan 30, 2024
  
  ad82bac6
30 Jan, 2024 4 commits
- Update quick start examples (#120) · 06175286
  Lianmin Zheng authored Jan 30, 2024
  
  06175286
- Format code (#118) · 4ea92f83
  Lianmin Zheng authored Jan 29, 2024
  
  4ea92f83
- Add qwen2 (#114) · 6b0af285
  Junyang Lin authored Jan 30, 2024
  
  6b0af285
- Improve the control of streaming and improve the first token latency in streaming (#117) · 6f560c76
  Lianmin Zheng authored Jan 29, 2024
  
  6f560c76
26 Jan, 2024 1 commit
- Fix Mistral model loading (#108) · cd687233
  Cody Yu authored Jan 26, 2024
```
Co-authored-by: johndun <dunavent.jm@gmail.com>
```
  cd687233
25 Jan, 2024 1 commit
- Dynamic model class loading (#101) · 3a581e99
  Cody Yu authored Jan 25, 2024
  
  3a581e99