Commits · 7b623fca0bfc561beaa3391c298656eb5187ce7a · OpenDAS / vllm_cscc

17 Feb, 2025 2 commits
- [VLM] Check required fields before initializing field config in `DictEmbeddingItems` (#13380) · 7b623fca
  Cyrus Leung authored Feb 17, 2025
  
  7b623fca
- [Feature][Spec Decode] Simplify the use of Eagle Spec Decode (#12304) · 46cdd595
  shangmingc authored Feb 17, 2025
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  46cdd595
16 Feb, 2025 1 commit
- [Quant] Add `SupportsQuant` to phi3 and clip (#13104) · 12913d17
  Kyle Sayers authored Feb 15, 2025
  
  12913d17
15 Feb, 2025 4 commits
- [Doc] [2/N] Add Fuyu E2E example for multimodal processor (#13331) · 367cb8ce
  Cyrus Leung authored Feb 15, 2025
  
  367cb8ce
- [AMD] [Model] DeepSeek tunings (#13199) · ed0de3e4
  rasmith authored Feb 15, 2025
  
  ed0de3e4
- [Bugfix] Fix qwen2.5-vl image processor (#13286) · 7fdaaf48
  Isotr0py authored Feb 15, 2025
  
  7fdaaf48
- [BugFix] Don't scan entire cache dir when loading model (#13302) · 90763256
  Nick Hill authored Feb 14, 2025
  
  90763256
14 Feb, 2025 7 commits
- [Core] Reduce TTFT with concurrent partial prefills (#10235) · 3bcb8c75
  Joe Runde authored Feb 14, 2025
```
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
Co-authored-by: Prashant Gupta <prashantgupta@us.ibm.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
```
  3bcb8c75
- [Quant][Perf] Use moe_wna16 kernel by default for MoEs with many experts (#13236) · 5e5c8e09
  Michael Goin authored Feb 14, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  5e5c8e09
- [Hardware][Gaudi][Bugfix] Fix error for guided decoding (#12317) · c9e2d644
  Yu-Zhou authored Feb 14, 2025
  
  c9e2d644
- [Core] choice-based structured output with xgrammar (#12632) · 7734e9a2
  Russell Bryant authored Feb 14, 2025
  
  7734e9a2
- [VLM] Keep track of whether prompt replacements have been applied (#13215) · 4da1f667
  Cyrus Leung authored Feb 14, 2025
  
  4da1f667
- Expand MLA to support most types of quantization (#13181) · f0b2da72
  Michael Goin authored Feb 14, 2025
  
  f0b2da72
- [Kernel][Bugfix] Refactor and Fix CUTLASS 2:4 Sparse Kernels (#13198) · c1e37bf7
  Tyler Michael Smith authored Feb 13, 2025
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  c1e37bf7
13 Feb, 2025 8 commits
- Optimize moe_align_block_size for deepseek_v3 (#12850) · 2344192a
  Michael Goin authored Feb 13, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  2344192a
- [Frontend] Add `/v1/audio/transcriptions` OpenAI API endpoint (#12909) · d84cef76
  Nicolò Lucchesi authored Feb 13, 2025
  
  d84cef76
- [VLM] Separate text-only and vision variants of the same model architecture (#13157) · 1bc3b5e7
  Cyrus Leung authored Feb 13, 2025
  
  1bc3b5e7
- [Misc] Qwen2.5-VL Optimization (#13155) · 02ed8a1f
  燃 authored Feb 13, 2025
  
  02ed8a1f
- [VLM] Merged multi-modal processor for Molmo (#12966) · c9d3ecf0
  Cyrus Leung authored Feb 13, 2025
  
  c9d3ecf0
- [VLM] Remove input processor from clip and siglip (#13165) · fa253f1a
  Isotr0py authored Feb 13, 2025
  
  fa253f1a
- Allow Unsloth Dynamic 4bit BnB quants to work (#12974) · cb944d58
  Daniel Han authored Feb 12, 2025
  
  cb944d58
- [VLM] Implement merged multimodal processor for Mllama (#11427) · bc55d130
  Isotr0py authored Feb 13, 2025
  
  bc55d130
12 Feb, 2025 5 commits
- [Bugfix] Allow fallback to AWQ from AWQMarlin at per-layer granularity (#13119) · 09972e71
  Michael Goin authored Feb 12, 2025
  
  09972e71
- [CORE] [QUANT] Support for GPTQModel's `dynamic` quantization per module override/control (#7086) · 36a08630
  Qubitium-ModelCloud authored Feb 13, 2025
  
  36a08630
- [Bugfix] Fix num video tokens calculation for Qwen2-VL (#13148) · 985b4a2b
  Cyrus Leung authored Feb 12, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  985b4a2b
- [Misc] AMD Build Improvements (#12923) · f1042e86
  Shiyan Deng authored Feb 12, 2025
  
  f1042e86
- [Model] IBM/NASA Prithvi Geospatial model (#12830) · 974dfd49
  Christian Pinto authored Feb 12, 2025
  
  974dfd49
11 Feb, 2025 3 commits
- [Bugfix] Guided decoding falls back to outlines when fails to import xgrammar (#12976) · 14ecab5b
  Yuan Tang authored Feb 11, 2025
```
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
```
  14ecab5b
- Fix initializing GGUF weights for ColumnParallelLinear when using tensor parallel > 1 (#13023) · 2b25b7d2
  Szymon Ożóg authored Feb 11, 2025
  
  2b25b7d2
- Set `torch_dtype` in `TransformersModel` (#13088) · ad977635
  Harry Mellor authored Feb 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  ad977635
10 Feb, 2025 3 commits
- [Model] Ultravox Model: Support v0.5 Release (#12912) · 08b2d845
  Farzad Abdolhosseini authored Feb 10, 2025
```
Signed-off-by: Farzad Abdolhosseini <farzad@fixie.ai>
```
  08b2d845
- [Bugfix] Clean up and fix multi-modal processors (#13012) · 51f0b5f7
  Cyrus Leung authored Feb 10, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  51f0b5f7
- [core] fix sleep mode and pytorch checkpoint compatibility (#13001) · b2496bb0
  youkaichao authored Feb 10, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  b2496bb0
08 Feb, 2025 6 commits
- [RFC] [Mistral] FP8 format (#10130) · d366ccc4
  Patrick von Platen authored Feb 08, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  d366ccc4
- [VLM] Merged multi-modal processor for GLM4V (#12449) · 86222a3d
  Jee Jee Li authored Feb 09, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  86222a3d
- [Misc] Add qwen2.5-vl BNB support (#12944) · 4c8dd12e
  Isotr0py authored Feb 08, 2025
  
  4c8dd12e
- [Misc] Log time consumption on weight downloading (#12926) · 011e612d
  Jun Duan authored Feb 08, 2025
  
  011e612d
- [Hardware][Intel-Gaudi] Enable long-contexts + LoRA support for Intel Gaudi (#12812) · 2880e21e
  Sanju C Sudhakaran authored Feb 08, 2025
```
Signed-off-by: Sanju C Sudhakaran <scsudhakaran@habana.ai>
```
  2880e21e
- [Bugfix] Fix Qwen2_5_VLForConditionalGeneration packed_modules_mapping (#12905) · 306923da
  Jee Jee Li authored Feb 08, 2025
  
  306923da
07 Feb, 2025 1 commit

[ROCm] [Feature] [Doc] [Dockerfile] [BugFix] Support Per-Token-Activation... · eaa92d44

TJian authored Feb 08, 2025

[ROCm] [Feature] [Doc] [Dockerfile] [BugFix] Support Per-Token-Activation Per-Channel-Weight FP8 Quantization Inferencing (#12501)

eaa92d44