Commits · da99b8e3d715a83d98ac0f548efc1907ec3731f5 · OpenDAS / vllm_cscc

"docs/source/dev/sampling_params.rst" did not exist on "6a9c583e73c75c8eab10a9c607cb096750b751a0"

07 Dec, 2024 1 commit

Merge branch 'v0.6.2-dev' into 'v0.6.2-dev' · da99b8e3

zhuwenwen authored Dec 07, 2024

Update offline_streaming_inference_chat_demo.py

See merge request dcutoolkit/deeplearing/vllm!49

da99b8e3

06 Dec, 2024 6 commits
- Update offline_streaming_inference_chat_demo.py · 28408cdf
  xuxz authored Dec 06, 2024
  
  28408cdf
- Merge branch 'v0.6.2-dev_wm' into 'v0.6.2-dev' · 1fe1a4b6
  zhuwenwen authored Dec 06, 2024
```
[feat]并行解码支持多卡推理

See merge request dcutoolkit/deeplearing/vllm!48
```
  1fe1a4b6
- [feat]并行解码支持多卡推理 · 4a4e3601
  王敏 authored Dec 06, 2024
  
  4a4e3601
- remove url about dcu · a1592b87
  zhuwenwen authored Dec 06, 2024
  
  a1592b87
- Merge branch 'v0.6.2-dev' of ssh://10.6.10.68:10022/dcutoolkit/deeplearing/vllm into v0.6.2-dev · 11bf5753
  zhuwenwen authored Dec 06, 2024
  
  11bf5753
- modify dcu urls display · 8516ba86
  zhuwenwen authored Dec 06, 2024
  
  8516ba86
05 Dec, 2024 10 commits
- Merge branch 'v0.6.2-dev' into 'v0.6.2-dev' · e06809f9
  zhuwenwen authored Dec 05, 2024
```
fix

See merge request dcutoolkit/deeplearing/vllm!47
```
  e06809f9
- fix · 8465317a
  xuxzh1 authored Dec 05, 2024
  
  8465317a
- Merge branch 'v0.6.2-dev' of ssh://10.6.10.68:10022/dcutoolkit/deeplearing/vllm into v0.6.2-dev · f6ce3afa
  zhuwenwen authored Dec 05, 2024
  
  f6ce3afa
- skip tests about cross-attn and not supported · 78800ecf
  zhuwenwen authored Dec 05, 2024
  
  78800ecf
- Merge branch 'v0.6.2-dev_wm' into 'v0.6.2-dev' · 1a313afb
  zhuwenwen authored Dec 05, 2024
```
[fix]修复单测test_mlp_correctness失败问题

See merge request dcutoolkit/deeplearing/vllm!45
```
  1a313afb
- update DCU info and skip tests same to nv · 129fce94
  zhuwenwen authored Dec 05, 2024
  
  129fce94
- [fix]修复单测test_mlp_correctness失败问题 · d623e721
  王敏 authored Dec 05, 2024
  
  d623e721
- Merge remote-tracking branch 'origin/v0.6.2-dev' into v0.6.2-dev · 217ee621
  王敏 authored Dec 05, 2024
  
  217ee621
- change AMD GPU and dcu to hcu · 3f78216a
  zhuwenwen authored Dec 05, 2024
  
  3f78216a
- added support for kernels tests with torch 2.3 · e150cf11
  zhuwenwen authored Dec 05, 2024
  
  e150cf11
04 Dec, 2024 5 commits
- remove unsupported tests from kernels and add pytest html · a3d96521
  zhuwenwen authored Dec 04, 2024
  
  a3d96521
- update offline_inference.py · 4646fe24
  zhuwenwen authored Dec 04, 2024
  
  4646fe24
- 修复新request kv cache移动错误 · f0021a4d
  王敏 authored Dec 04, 2024
  
  f0021a4d
- update tensorized_path · 03d145db
  zhuwenwen authored Dec 04, 2024
  
  03d145db
- support falcon and optimize layout · 9ddee6b1
  zhuwenwen authored Dec 04, 2024
  
  9ddee6b1
03 Dec, 2024 8 commits
- Merge branch '0.6.2-w8a8' into 'v0.6.2-dev' · 2d5a25cd
  zhuwenwen authored Dec 03, 2024
```
0.6.2 w8a8

See merge request dcutoolkit/deeplearing/vllm!43
```
  2d5a25cd
- 修改cutlass 单测 · 26513bb5
  gaoqiong authored Dec 03, 2024
  
  26513bb5
- add large_gpu_test · 0dc55ec0
  zhuwenwen authored Dec 03, 2024
  
  0dc55ec0
- 增加w8a8的triton调度支持 · 1a9775b8
  gaoqiong authored Dec 03, 2024
  
  1a9775b8
- update tests · 47be5a1c
  zhuwenwen authored Dec 03, 2024
  
  47be5a1c
- 增加w8a8的triton调度支持 · 1c77f16e
  gaoqiong authored Dec 03, 2024
  
  1c77f16e
- Merge branch 'v0.6.2-dev_wm' into 'v0.6.2-dev' · 7bdb7e63
  zhuwenwen authored Dec 03, 2024
```
[fix]修复llm_engine.py 越界报错

See merge request dcutoolkit/deeplearing/vllm!42
```
  7bdb7e63
- [fix]修复llm_engine.py 越界报错 · acdbc978
  王敏 authored Dec 03, 2024
  
  acdbc978
02 Dec, 2024 2 commits
- add ChatGLMForConditionalGeneration · 6ebda263
  zhuwenwen authored Dec 02, 2024
  
  6ebda263
- update qwen2 supported_lora_modules · d5723fbb
  zhuwenwen authored Dec 02, 2024
  
  d5723fbb
29 Nov, 2024 1 commit
- add VLLM_OPTEST_URLS_PORT to load https from local · 41b09879
  zhuwenwen authored Nov 29, 2024
  
  41b09879
28 Nov, 2024 4 commits
- update tests · 4c8e606b
  zhuwenwen authored Nov 28, 2024
  
  4c8e606b
- update lm_head layout of chatglm · 77ae0f0d
  zhuwenwen authored Nov 28, 2024
  
  77ae0f0d
- update tests · 2ff1c360
  zhuwenwen authored Nov 28, 2024
  
  2ff1c360
- Merge branch 'v0.6.2-dev_wm' into 'v0.6.2-dev' · 201768d5
  zhuwenwen authored Nov 28, 2024
```
优化medusa 推理

See merge request dcutoolkit/deeplearing/vllm!41
```
  201768d5
27 Nov, 2024 3 commits
- update tests · 87a2e37f
  zhuwenwen authored Nov 27, 2024
  
  87a2e37f
- 1.优化medusa推理，节省cpu耗时 · 28375803
  王敏 authored Nov 27, 2024
```
2.更新medusa readme
3.解决benchmark_moe报错问题
```
  28375803
- 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