Commits · 61acfc45bcf44de6e5a14c82906bbb7a33940443 · OpenDAS / vllm_cscc

"lib/llm/src/vscode:/vscode.git/clone" did not exist on "9ae98ed7f98ad3b4865dadfa1c838439d73475be"

21 May, 2025 2 commits
- [Bugfix] config.head_dim is now explicitly set to None (#18432) · 0c15c2e4
  Gregory Shtrasberg authored May 21, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  0c15c2e4
- [TPU] Re-enable the Pallas MoE kernel (#18025) · 3b17ea26
  Michael Goin authored May 20, 2025
```
Signed-off-by: Michael Goin <mgoin64@gmail.com>
```
  3b17ea26
20 May, 2025 4 commits
- [Model] use AutoWeightsLoader for bloom (#18300) · e1f5a71e
  Calvin Chen authored May 21, 2025
```
Signed-off-by: calvin chen <120380290@qq.com>
```
  e1f5a71e
- [Minor] Rename quantization nvfp4 to modelopt_fp4 (#18356) · f4a8a374
  Michael Goin authored May 20, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  f4a8a374
- [Bugfix] fix adding bias twice in ipex GPTQ quantization (#18363) · bca55b55
  Random Fly authored May 20, 2025
```
Signed-off-by: rand-fly <randfly@outlook.com>
```
  bca55b55
- [Misc] Allow `AutoWeightsLoader` to skip loading weights with specific substr in name (#18358) · f07a673e
  Isotr0py authored May 20, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  f07a673e
19 May, 2025 7 commits
- Neuron up mistral (#18222) · dc1440cf
  Satyajith Chilappagari authored May 19, 2025
```
Signed-off-by: Satyajith Chilappagari <satchill@amazon.com>
```
  dc1440cf
- Add files via uploadAdd fused MoE kernel tuning configs (fp8_w8a8) for... · 7937c2fd
  sunyicode0012 authored May 20, 2025
```
Add files via uploadAdd fused MoE kernel tuning configs (fp8_w8a8) for DeepSeek V3/R1 on a single-node 8x NVIDIA H20 96GB setup (#18337)
```
  7937c2fd
- [Feature]Add support for models quantized with AutoRound (#17850) · e2ee1e8e
  Wenhua Cheng authored May 20, 2025
```
Signed-off-by: wenhuach21 <wenhua.cheng@intel.com>
```
  e2ee1e8e
- [Quantization] Pool model support bitsandbytes (#18087) · 6781af56
  Jee Jee Li authored May 20, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  6781af56
- [BugFix] [Vul] Add missing `usedforsecurity=False` in MD5 hashing to enable FIPS (#18319) · d637b960
  Shaoyu Yang authored May 19, 2025
```
Signed-off-by: cascade812 <cascade812@outlook.com>
Signed-off-by: shaoyuyoung <shaoyuyoung@gmail.com>
Co-authored-by: cascade <cascade812@outlook.com>
```
  d637b960
- fix: Add type specifications for CLI arguments in tensorizer options (#18314) · 275c5dae
  CYJiang authored May 19, 2025
  
  275c5dae
- [Spec Decode][V0] Fix spec decode correctness test in V0 eagle/medusa (#18175) · 9da1095d
  wwl2755 authored May 18, 2025
```
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
```
  9da1095d
18 May, 2025 2 commits
- Fix copy-paste error in phi4mm image processing (#18315) · 4fb349f6
  Lifu Huang authored May 18, 2025
```
Signed-off-by: Lifu Huang <lifu.hlf@gmail.com>
```
  4fb349f6
- [Model] Use sigmoid for single-label classification (#18313) · 908733ac
  22quinn authored May 18, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  908733ac
17 May, 2025 1 commit
- [Model] use AutoWeightsLoader for solar (#18113) · 9214e606
  rongfu.leng authored May 17, 2025
  
  9214e606
16 May, 2025 5 commits
- [Sampler] Adapt to FlashInfer 0.2.3 sampler API (#15777) · 7fdfa015
  Bowen Wang authored May 16, 2025
```
Signed-off-by: Bowen Wang <abmfy@icloud.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  7fdfa015
- [Model] Use autoweightloader for dbrx (#18251) · 87d87147
  learner0810 authored May 16, 2025
```
Signed-off-by: learner0810 <zhongjun.li@daocloud.io>
```
  87d87147
- use ceil_div in cutlass block scaling shape check (#17918) · e23564cb
  Lain authored May 16, 2025
  
  e23564cb
- [PERF] Speed up Qwen2.5-VL model by speed up rotary position embedding (#17973) · 67da5720
  Vadim Gimpelson authored May 16, 2025
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@centml.ai>
```
  67da5720
- [Model] vLLM v1 supports Medusa (#17956) · f4937a51
  Sky Lee authored May 16, 2025
```
Signed-off-by: lisiqi23 <lisiqi23@xiaomi.com>
Signed-off-by: skylee-01 <497627264@qq.com>
Co-authored-by: lisiqi23 <lisiqi23@xiaomi.com>
```
  f4937a51
15 May, 2025 6 commits
- [Bugfix] [ROCm]: Remove assertion logic when using AITER fused moe in... · 92540529
  TJian authored May 16, 2025
```
[Bugfix] [ROCm]: Remove assertion logic when using AITER fused moe in unquantizedMethod to reenable LLama4 BF16 (#18205)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  92540529
- Update deprecated type hinting in `model_loader` (#18130) · 07ad2712
  Harry Mellor authored May 15, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  07ad2712
- fix: typos (#18151) · a9944aab
  omahs authored May 15, 2025
```
Signed-off-by: omahs <73983677+omahs@users.noreply.github.com>
```
  a9944aab
- [Bugfix] Fix FusedMoEPrepareAndFinalize for cuda-disalike backends (#18178) · 70f8b967
  Mengqing Cao authored May 15, 2025
```
Signed-off-by: Mengqing Cao <cmq0113@163.com>
```
  70f8b967
- [Model] Allow the use of sliding window in Qwen2 (#17772) · dd2a9459
  inkcherry authored May 15, 2025
```
Signed-off-by: inkcherry <mingzhi.liu@intel.com>
```
  dd2a9459
- Update deprecated type hinting in `models` (#18132) · 26d04193
  Harry Mellor authored May 15, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  26d04193
14 May, 2025 13 commits
- Add support for loading torchao models with `AOPerModuleConfig` (#17826) · 79747367
  Jerry Zhang authored May 14, 2025
```
Signed-off-by: Jerry Zhang <jerryzh168@gmail.com>
```
  79747367
- Modularize fused experts and integrate PPLX kernels (#15956) · f9c069c8
  bnellnm authored May 14, 2025
  
  f9c069c8
- [V1][Spec Decode] Share input embedding of target model with EAGLE draft model... · 418d2f8b
  Ekagra Ranjan authored May 14, 2025
```
[V1][Spec Decode] Share input embedding of target model with EAGLE draft model to free ~1GB for llama 3 model (#17326)
Co-authored-by: root <root@ekagra-8xh100.us-east5-a.c.serving-efficiency-poc.internal>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  418d2f8b
- [Model] GritLM supports other attention backends (#18109) · d62a076e
  Cyrus Leung authored May 14, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  d62a076e
- [FEAT] [ROCm]: Add AITER CK 2 Stages MoE support (#17110) · 612c2edb
  TJian authored May 14, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  612c2edb
- [Bugfix] Fix QKVCrossParallelLinear::sync_weight_attrs for PyTorch compile (#17844) · 38fe728d
  Andrzej Kotłowski authored May 14, 2025
```
Signed-off-by: Andrzej Kotłowski <akotlowski@habana.ai>
```
  38fe728d
- [Model] Add packed_modules_mapping for Qwen3-MOE (#18118) · 63dc3426
  Jee Jee Li authored May 14, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  63dc3426
- [New Model]: support GTE NewModel (#17986) · 63ad6222
  wang.yuqi authored May 14, 2025
  
  63ad6222
- [BugFix][AMD] Compatible patch for AITER lib after 04/20 (#17912) · 4f8b3732
  qli88 authored May 14, 2025
```
Signed-off-by: Qiang Li <qiang.li2@amd.com>
```
  4f8b3732
- [FEAT] [ROCm] [V1]: Add AITER biased group topk for DeepSeekV3 (#17955) · 2d912fb6
  vllmellm authored May 14, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  2d912fb6
- [Bugfix] Fix FP8 Marlin MoE and enable for compressed-tensors models (#18026) · 9a2a6357
  Michael Goin authored May 13, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  9a2a6357
- [core][distributed] add ep group and all2all interface (#18077) · 6266c57b
  youkaichao authored May 14, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  6266c57b
- [Hardware/NVIDIA/Modelopt] Fix modelopt forward method for v1 torch.compile (#18101) · 65f0f74b
  Pavani Majety authored May 13, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  65f0f74b