Commits · afd0da2186c1d58fb48e138df0a2f548612b5d7d · OpenDAS / vllm_cscc

28 Jan, 2025 1 commit
- Update `pre-commit` hooks (#12475) · 823ab796
  Harry Mellor authored Jan 28, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  823ab796
17 Jan, 2025 1 commit
- [Misc][LoRA] Improve the readability of LoRA error messages (#12102) · 07934cc2
  Jee Jee Li authored Jan 17, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  07934cc2
12 Jan, 2025 1 commit

[Hardware][CPU] Multi-LoRA implementation for the CPU backend (#11100) · 8bddb735

Akshat Tripathi authored Jan 12, 2025


Signed-off-by: Akshat Tripathi <akshat@krai.ai>
Signed-off-by: Oleg Mosalov <oleg@krai.ai>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Oleg Mosalov <oleg@krai.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Isotr0py <2037008807@qq.com>

8bddb735

07 Jan, 2025 1 commit

[Kernel][LoRA]Punica prefill kernels fusion (#11234) · b2785579

Jee Jee Li authored Jan 07, 2025


Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: Abatom <abzhonghua@gmail.com>
Co-authored-by: Zhonghua Deng <abatom@163.com>

b2785579

01 Jan, 2025 1 commit
- [Misc] Optimize Qwen2-VL LoRA test (#11663) · 11d8a091
  Jee Jee Li authored Jan 01, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  11d8a091
31 Dec, 2024 1 commit

[Misc][LoRA] Support Rank Stabilized LoRA (RSLoRA) (#6909) · 82c49d32

John Giorgi authored Dec 31, 2024


Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

82c49d32

27 Dec, 2024 1 commit
- [MODEL] LoRA support for Jamba model (#11209) · 55509c21
  ErezSC42 authored Dec 27, 2024
```
Signed-off-by: Erez Schwartz <erezs@ai21.com>
```
  55509c21
26 Dec, 2024 1 commit
- [Misc][LoRA] Fix LoRA weight mapper (#11495) · aa25985b
  Jee Jee Li authored Dec 26, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  aa25985b
24 Dec, 2024 2 commits
- [Bugfix] Fix Qwen2-VL LoRA weight loading (#11430) · b1b1038f
  Jee Jee Li authored Dec 24, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  b1b1038f
- [feat]添加qwen的lora单测 · 3f29b4a8
  王敏 authored Dec 24, 2024
  
  3f29b4a8
22 Dec, 2024 1 commit
- [Bugfix] Fix fully sharded LoRAs with Mixtral (#11390) · f1d1bf62
  Jason T. Greene authored Dec 22, 2024
```
Signed-off-by: Jason Greene <jason.greene@redhat.com>
```
  f1d1bf62
18 Dec, 2024 1 commit
- [Bugfix] fix minicpmv test (#11304) · ca5f54a9
  Joe Runde authored Dec 18, 2024
```
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
```
  ca5f54a9
11 Dec, 2024 1 commit
- [Misc] LoRA + Chunked Prefill (#9057) · d5c5154f
  Aurick Qiao authored Dec 10, 2024
  
  d5c5154f
10 Dec, 2024 2 commits

[Misc][LoRA] Add PEFTHelper for LoRA (#11003) · d05f8867
Jee Jee Li authored Dec 10, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
d05f8867

test_audio文件将TEST_AUDIO_URLS改为本地；testchat文件360行路径改为本地；test_metrics文件197行将base_... · 859566e0

guanyu authored Dec 10, 2024

test_audio文件将TEST_AUDIO_URLS改为本地；testchat文件360行路径改为本地；test_metrics文件197行将base_url从0.0.0.0改为localhost；test_run_batch将INPUT_BATCH，INVALID_INPUT_BATCH,INPUT_EMBEDDING_BATCH改为原来的格式；test_tokenizer_group将18行的gpt路径改为修改后的路径；test_braodcast将model的判断改为if llava-hf/llava-1.5-7b-hf in model

859566e0

09 Dec, 2024 1 commit
- [Misc][LoRA] Abstract PunicaWrapper (#10955) · ca871491
  Jee Jee Li authored Dec 10, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  ca871491
05 Dec, 2024 1 commit
- [Misc][LoRA] Clean up the function interface of Punica (#10917) · 571da8fc
  Jee Jee Li authored Dec 05, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  571da8fc
04 Dec, 2024 1 commit
- [LoRA] Change lora_tokenizers capacity (#10796) · 01d079fd
  Xin Yang authored Dec 04, 2024
```
Signed-off-by: Xin Yang <xyang19@gmail.com>
```
  01d079fd
02 Dec, 2024 1 commit
- [Misc][LoRA] Move the implementation of lora bias to punica.py (#10829) · b45f0d79
  Jee Jee Li authored Dec 03, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  b45f0d79
29 Nov, 2024 1 commit
- add VLLM_OPTEST_URLS_PORT to load https from local · 41b09879
  zhuwenwen authored Nov 29, 2024
  
  41b09879
27 Nov, 2024 1 commit
- add VLLM_OPTEST_MODELS_PATH/OPTEST_MODELS_PATH to load models from local path... · 3c9817d2
  zhuwenwen authored Nov 27, 2024
```
add VLLM_OPTEST_MODELS_PATH/OPTEST_MODELS_PATH  to load models from local path instead of Hugging Face Hub
```
  3c9817d2
24 Nov, 2024 1 commit

[Bugfix] Fix LoRA weight sharding (#10450) · 1700c543

Jee Jee Li authored Nov 24, 2024


Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

1700c543

21 Nov, 2024 1 commit
- [Kernel] Register punica ops directly (#10522) · 2385b60d
  Jee Jee Li authored Nov 22, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  2385b60d
15 Nov, 2024 3 commits
- [fix]修复单测test_punica_variation报共享内存不足的问题 · 137e8a16
  王敏 authored Nov 15, 2024
  
  137e8a16
- [fix]回退test_long_context中限制输入长度修改 · 9736caa9
  王敏 authored Nov 15, 2024
  
  9736caa9
- [fix]修复test_long_context中报错问题，单测依然无法通过，nv也是同样的问题 · 1d6cfb11
  王敏 authored Nov 15, 2024
  
  1d6cfb11
12 Nov, 2024 2 commits
- [LoRA] Adds support for bias in LoRA (#5733) · 8a06428c
  Umesh authored Nov 12, 2024
```
Signed-off-by: Umesh Deshpande <udeshpa@us.ibm.com>
Co-authored-by: Umesh Deshpande <udeshpa@us.ibm.com>
```
  8a06428c
- [Misc][LoRA] Replace hardcoded cuda device with configurable argument (#10223) · 7f5edb59
  Jee Jee Li authored Nov 12, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  7f5edb59
11 Nov, 2024 1 commit
- [LoRA][Kernel] Remove the unused libentry module (#10214) · 36e4acd0
  Jee Jee Li authored Nov 11, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  36e4acd0
04 Nov, 2024 1 commit
- [Bugfix][CI/Build][Hardware][AMD] Shard ID parameters in AMD tests running parallel jobs (#9279) · 5208dc7a
  hissu-hyvarinen authored Nov 04, 2024
```
Signed-off-by: Hissu Hyvarinen <hissu.hyvarinen@amd.com>
```
  5208dc7a
02 Nov, 2024 2 commits
- [3/N] model runner pass the whole config to model (#9958) · cea808f3
  youkaichao authored Nov 02, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  cea808f3
- [2/N] executor pass the complete config to worker/modelrunner (#9938) · e8937954
  youkaichao authored Nov 02, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  e8937954
29 Oct, 2024 1 commit
- [Hardware] using current_platform.seed_everything (#9785) · 622b7ab9
  wangshuai09 authored Oct 29, 2024
```
Signed-off-by: wangshuai09 <391746016@qq.com>
```
  622b7ab9
28 Oct, 2024 1 commit
- [Hardware][ROCM] using current_platform.is_rocm (#9642) · 4e2d95e3
  wangshuai09 authored Oct 28, 2024
```
Signed-off-by: wangshuai09 <391746016@qq.com>
```
  4e2d95e3
22 Oct, 2024 2 commits
- [CI/Build][LoRA] Temporarily fix long context failure issue (#9579) · a48e3ec0
  Jee Jee Li authored Oct 22, 2024
  
  a48e3ec0
- 🐛 Fixup more test failures from memory profiling (#9563) · ef7faad1
  Joe Runde authored Oct 21, 2024
```
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
```
  ef7faad1
18 Oct, 2024 2 commits
- [MISC] Consolidate cleanup() and refactor offline_inference_with_prefix.py (#9510) · d11bf435
  Cody Yu authored Oct 18, 2024
  
  d11bf435
- [Model] Add user-configurable task for models that support both generation and embedding (#9424) · 051eaf6d
  Cyrus Leung authored Oct 19, 2024
  
  051eaf6d
16 Oct, 2024 1 commit
- [Misc] Standardize RoPE handling for Qwen2-VL (#9250) · 7e7eae33
  Cyrus Leung authored Oct 16, 2024
  
  7e7eae33
11 Oct, 2024 1 commit
- [Misc][LoRA] Support loading LoRA weights for target_modules in reg format (#9275) · 36ea7907
  Jee Jee Li authored Oct 11, 2024
  
  36ea7907