Commits · b4c4464df67445ef07a28b12d8e39701d77c39db · OpenDAS / vllm_cscc

17 Jun, 2025 1 commit

[fix]1.修复medusa、scorer等并行解码单测；2.修复moe... · 8db76782

王敏 authored Jun 17, 2025

[fix]1.修复medusa、scorer等并行解码单测；2.修复moe kernel单测问题，优化代码；3.修复rejection_sampler中test_compare_nonflashinfer_backend单测问题

8db76782

13 Jun, 2025 3 commits
- [fix]修复并行解码eagle和mlp相关单测问题 · 08cb5d8f
  王敏 authored Jun 13, 2025
  
  08cb5d8f
- 解耦w8a8 的gemm以及moe算子相关实现 · 942368c7
  gaoqiong authored Jun 13, 2025
  
  942368c7
- [New Model]: Support Qwen3 Embedding & Reranker · 9bcbaafc
  zhuwenwen authored Jun 13, 2025
  
  9bcbaafc
12 Jun, 2025 2 commits
- 修复qwen3-moe的awq配置导致fp16加载错误，修复dpsk-moe手写算子首字耗时增加问题 · 99ffef47
  zhuwenwen authored Jun 12, 2025
  
  99ffef47
- update qwen2&2.5-vl prefill interface and fix pixtral run error · 4fd5389b
  zhuwenwen authored Jun 12, 2025
  
  4fd5389b
10 Jun, 2025 1 commit
- Update qwen3_moe.py · 07c69390
  zhuwenwen authored Jun 10, 2025
  
  07c69390
06 Jun, 2025 1 commit
- [Model] Add VLLM_USE_NN to use nn layout · 6880bf15
  zhuwenwen authored Jun 06, 2025
  
  6880bf15
05 Jun, 2025 2 commits
- 新增qwen3 fusemoe优化支持 · 1cb37dab
  yangql authored Jun 05, 2025
  
  1cb37dab
- 修改deepseelk block-int8 权重处理流程，增加per-channel bestconfig配置以及首次triton warmup代码 · 40b94473
  gaoqiong authored Jun 05, 2025
  
  40b94473
04 Jun, 2025 1 commit
- 修复qwen3-moe-awq的bug问题 · 1a4e4cad
  yangql authored Jun 04, 2025
  
  1a4e4cad
27 May, 2025 2 commits
- [feat]适配sgl moe_fused_gate kernel · 0b229519
  王敏 authored May 27, 2025
  
  0b229519
- 修复0.8.5 config找不到的bug · 823b3332
  gaoqiong authored May 27, 2025
  
  823b3332
26 May, 2025 1 commit
- update qwen3 moe inference · 7bdb03ea
  zhuwenwen authored May 26, 2025
  
  7bdb03ea
23 May, 2025 1 commit
- tbo增加ds int8支持，修改tb zerooverhead环境变量到envs.py中统一管理 · dbbb148b
  lizhigong authored May 23, 2025
  
  dbbb148b
22 May, 2025 2 commits
- 优化awq权重转换的方式，修复可能会导致蒸馏模型加载时报错的bug · a94ed3ea
  yangql authored May 22, 2025
  
  a94ed3ea
- fix tbo to support deepseek · 0cc7c880
  lizhigong authored May 22, 2025
  
  0cc7c880
20 May, 2025 1 commit
- support qiyuan-8b-v2 and FM9GForCausalLM · 8fb5dea5
  zhuwenwen authored May 20, 2025
  
  8fb5dea5
16 May, 2025 1 commit
- update qwen3_moe.py · 9b0aa006
  zhuwenwen authored May 16, 2025
  
  9b0aa006
15 May, 2025 1 commit
- fix qwen3-235b run error and remove update_environment_variables of hip · 3f9af065
  zhuwenwen authored May 15, 2025
  
  3f9af065
13 May, 2025 1 commit
- add qwen3 moe configs · 09e372e7
  zhuwenwen authored May 13, 2025
```
support telechat2 and glm4 nn layout
remove log of request_id
```
  09e372e7
06 May, 2025 1 commit
- support qwen3-moe nn layout · 4dc24bc8
  zhuwenwen authored May 06, 2025
  
  4dc24bc8
28 Apr, 2025 5 commits
- [Misc] Clean up Qwen2.5-Omni code (#17301) · 8b464d96
  Cyrus Leung authored Apr 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  8b464d96
- [Bugfix] Add missing `get_language_model` to new MLLMs (#17300) · 344e193b
  Cyrus Leung authored Apr 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  344e193b
- [Model] Add Granite Speech Support (#16246) · fa93cd9f
  Alex Brooks authored Apr 28, 2025
```
Signed-off-by: Alex-Brooks <Alex.brooks@ibm.com>
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
```
  fa93cd9f
- [Minor][Models] Pass partial_rotary_factor parameter to rope (#17266) · 7fcc4223
  Wanrui Dai authored Apr 28, 2025
```
Signed-off-by: evian <eviantai@u.nus.edu>
Co-authored-by: evian <eviantai@u.nus.edu>
```
  7fcc4223
- [Bugfix] Fix Mistral3 spatial merge error (#17270) · cb3f2d8d
  Michael Goin authored Apr 27, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  cb3f2d8d
27 Apr, 2025 1 commit
- [Bugfix] Fix QWen2 VL multimodal mapping (#17240) · 4283a28c
  Jee Jee Li authored Apr 27, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  4283a28c
26 Apr, 2025 2 commits
- [Minor][Models] Fix Return Types of Llama & Eagle (#17220) · b2789112
  Woosuk Kwon authored Apr 25, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  b2789112
- [Bugfix] gemma[2,3] interleaved attention when sliding window is disabled (#17180) · 8de2901f
  Chen Zhang authored Apr 26, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  8de2901f
25 Apr, 2025 2 commits

[V1][Spec Decode] EAGLE-3 Support (#16937) · a0e619e6

Benjamin Chislett authored Apr 25, 2025


Signed-off-by: Bryan Lu <yuzhelu@amazon.com>
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Co-authored-by: Bryan Lu <yuzhelu@amazon.com>

a0e619e6

fix float16 support for kimi-vl (#17156) · 69bff9bc
Zaida Zhou authored Apr 25, 2025
```
Co-authored-by: zhouzaida <zhouzaida@msh.team>
```
69bff9bc

24 Apr, 2025 4 commits
- [Misc] Remove OLMo2 config copy (#17066) · b0c1f620
  Isotr0py authored Apr 24, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  b0c1f620
- [Chore] Remove Sampler from Model Code (#17084) · b411418f
  Woosuk Kwon authored Apr 24, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  b411418f
- fix llama and qwen layout · 61898ea3
  zhuwenwen authored Apr 24, 2025
  
  61898ea3
- [Quantization]add prefix for commandA quantized model (#17017) · 6b2427f9
  Chen Xia authored Apr 23, 2025
  
  6b2427f9
22 Apr, 2025 3 commits
- [Bugfix] Fix distributed bug again in Qwen2.5-VL & Qwen2.5-Omni (#16974) · 571e8dd6
  Yang Fan authored Apr 22, 2025
```
Signed-off-by: fyabc <suyang.fy@alibaba-inc.com>
```
  571e8dd6
- [Model] Use autoweightloader for mamba (#16950) · 2689d5c0
  Flora Feng authored Apr 22, 2025
```
Signed-off-by: sfeng33 <4florafeng@gmail.com>
```
  2689d5c0
- [Bugfix] Fix GLM rotary_dim issue and support v1 · 7f3dec12
  zhuwenwen authored Apr 22, 2025
```
Fix glm4.py residual bug
```
  7f3dec12
21 Apr, 2025 1 commit
- [Bugfix] Fix GLM rotary_dim issue and support v1 (#16912) · 55d6d3fd
  Isotr0py authored Apr 21, 2025
```
Signed-off-by: isotr0py <2037008807@qq.com>
```
  55d6d3fd