Commits · eb5cb5e5280c83226408c3d1e30928364c6258db · OpenDAS / vllm_cscc

23 Jan, 2025 4 commits

[BugFix] Fix parameter names and `process_after_weight_loading` for W4A16 MoE... · eb5cb5e5

Dipika Sikka authored Jan 23, 2025


[BugFix] Fix parameter names and `process_after_weight_loading` for W4A16 MoE Group Act Order  (#11528)
Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>

eb5cb5e5

[FP8][Kernel] Dynamic kv cache scaling factors computation (#11906) · e97f802b

Gregory Shtrasberg authored Jan 23, 2025


Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>

e97f802b

[Bugfix] Fix k_proj's bias for whisper self attention (#12342) · c5b4b11d
Isotr0py authored Jan 23, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
c5b4b11d
[AMD][Quantization] Add TritonScaledMMLinearKernel since int8 is broken for AMD (#12282) · 68c4421b
rasmith authored Jan 22, 2025
```
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
```
68c4421b

22 Jan, 2025 7 commits
- [Misc] Improve the readability of BNB error messages (#12320) · 84bee4bd
  Jee Jee Li authored Jan 23, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  84bee4bd
- [Doc] Add docs for prompt replacement (#12318) · 6609cdf0
  Cyrus Leung authored Jan 22, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  6609cdf0
- [Bugfix][VLM] Fix mixed-modality inference backward compatibility for V0 (#12313) · 16366ee8
  Roger Wang authored Jan 22, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  16366ee8
- [Model][Bugfix]: correct Aria model output (#12309) · 528dbcac
  zhou fan authored Jan 22, 2025
```
Signed-off-by: xffxff <1247714429@qq.com>
```
  528dbcac
- [VLM] Avoid unnecessary tokenization (#12310) · cd7b6f08
  Cyrus Leung authored Jan 22, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  cd7b6f08
- [ci/lint] Add back default arg for pre-commit (#12279) · 64ea24d0
  Kevin H. Luu authored Jan 21, 2025
```
Signed-off-by: kevin <kevin@anyscale.com>
```
  64ea24d0
- [VLM] Simplify post-processing of replacement info (#12269) · df76e5af
  Cyrus Leung authored Jan 22, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  df76e5af
21 Jan, 2025 7 commits
- [Misc] Set default backend to SDPA for get_vit_attn_backend (#12235) · fa9ee081
  wangxiyuan authored Jan 22, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  fa9ee081
- [Misc] Remove redundant TypeVar from base model (#12248) · f2e9f2a3
  Cyrus Leung authored Jan 21, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  f2e9f2a3
- [Misc]Add BNB quantization for PaliGemmaForConditionalGeneration (#12237) · 1f1542af
  Jee Jee Li authored Jan 21, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  1f1542af
- [Misc] Rename `MultiModalInputsV2 -> MultiModalInputs` (#12244) · 96912550
  Cyrus Leung authored Jan 21, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  96912550
- [BugFix] Fix GGUF tp>1 when vocab_size is not divisible by 64 (#12230) · 5fe6bf29
  Nicolò Lucchesi authored Jan 21, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  5fe6bf29
- [AMD][Build] Porting dockerfiles from the ROCm/vllm fork (#11777) · d4b62d46
  Gregory Shtrasberg authored Jan 20, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  d4b62d46
- [bugfix] catch xgrammar unsupported array constraints (#12210) · 06a760d6
  Cheng Kuan Yong Jason authored Jan 21, 2025
```
Signed-off-by: Jason Cheng <jasoncky96@gmail.com>
```
  06a760d6
20 Jan, 2025 3 commits
- [Model] Upgrade Aria to transformers 4.48 (#12203) · b37d8279
  Cyrus Leung authored Jan 20, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  b37d8279
- [Core] Interface for accessing model from `VllmRunner` (#10353) · 59a0192f
  Cyrus Leung authored Jan 20, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  59a0192f
- [Model] Add Qwen2 PRM model support (#12202) · 83609791
  Isotr0py authored Jan 20, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  83609791
19 Jan, 2025 6 commits
- [Model] Support for fairseq2 Llama (#11442) · bbe5f9de
  Martin Gleize authored Jan 19, 2025
```
Signed-off-by: Martin Gleize <mgleize@meta.com>
Co-authored-by: mgleize user <mgleize@a100-st-p4de24xlarge-4.fair-a100.hpcaas>
```
  bbe5f9de
- [V1] Add V1 support of Qwen2-VL (#12128) · 81763c58
  Roger Wang authored Jan 19, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: imkero <kerorek@outlook.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  81763c58
- [Misc] Add BNB support to GLM4-V model (#12184) · edaae198
  Isotr0py authored Jan 19, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  edaae198
- [Bugfix] Fix multi-modal processors for transformers 4.48 (#12187) · 630eb5b5
  Cyrus Leung authored Jan 19, 2025
  
  630eb5b5
- [BUGFIX] Move scores to float32 in case of running xgrammar on cpu (#12152) · 4e94951b
  Michal Adamczyk authored Jan 19, 2025
```
Signed-off-by: Michal Adamczyk <madamczyk@habana.ai>
```
  4e94951b
- [Misc] Support register quantization method out-of-tree (#11969) · 32eb0da8
  yancong authored Jan 19, 2025
  
  32eb0da8
18 Jan, 2025 1 commit
- [Model] Port deepseek-vl2 processor, remove dependency (#12169) · 02798eca
  Isotr0py authored Jan 18, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  02798eca
17 Jan, 2025 2 commits
- [AMD][FP8] Using MI300 FP8 format on ROCm for block_quant (#12134) · b5b57e30
  Gregory Shtrasberg authored Jan 17, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  b5b57e30
- [CI/Build][CPU][Bugfix] Fix CPU CI (#12150) · d4e61945
  Li, Jiang authored Jan 17, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  d4e61945
16 Jan, 2025 6 commits
- [Model] Add support for deepseek-vl2-tiny model (#12068) · 62b06ba2
  Isotr0py authored Jan 17, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  62b06ba2
- [Bugfix] Fix max image feature size for Llava-one-vision (#12104) · 874f7c29
  Roger Wang authored Jan 16, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  874f7c29
- Support torchrun and SPMD-style offline inference (#12071) · bf53e0c7
  youkaichao authored Jan 16, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  bf53e0c7
- [Bugfix] Remove hardcoded `head_size=256` for Deepseek v2 and v3 (#12067) · dd7c9ad8
  Isotr0py authored Jan 16, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  dd7c9ad8
- Various cosmetic/comment fixes (#12089) · 9aa1519f
  Michael Goin authored Jan 16, 2025
```
Signed-off-by: mgoin <michael@neuralmagic.com>
```
  9aa1519f
- [Core] Default to using per_token quantization for fp8 when cutlass is supported. (#8651) · fa0050db
  Elfie Guo authored Jan 15, 2025
```
Signed-off-by: mgoin <michael@neuralmagic.com>
Co-authored-by: Michael Goin <mgoin@redhat.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
```
  fa0050db
15 Jan, 2025 4 commits
- [Misc][Quark] Upstream Quark format to VLLM (#10765) · de0526f6
  kewang-xlnx authored Jan 16, 2025
```
Signed-off-by: kewang-xlnx <kewang@xilinx.com>
Signed-off-by: kewang2 <kewang2@amd.com>
Co-authored-by: kewang2 <kewang2@amd.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
```
  de0526f6
- [Model]: Support internlm3 (#12037) · 97eb97b5
  RunningLeon authored Jan 15, 2025
  
  97eb97b5
- Fix: cases with empty sparsity config (#12057) · cbe94391
  Rahul Tuli authored Jan 15, 2025
```
Signed-off-by: Rahul Tuli <rahul@neuralmagic.com>
```
  cbe94391
- [Kernel] Support MulAndSilu (#11624) · 42f5e7c5
  Jee Jee Li authored Jan 15, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  42f5e7c5