Commits · 38e599d6a84bb7477030a5488035cd23f529b644 · OpenDAS / vllm_cscc

"vscode:/vscode.git/clone" did not exist on "2c5bde718367e84f5c5326fdd4367f7c415be51c"

15 Dec, 2024 4 commits
- [Bugfix] Fix error handling of unsupported sliding window (#11213) · 96d673e0
  Cyrus Leung authored Dec 16, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  96d673e0
- [Misc] Clean up multi-modal processor (#11207) · b10609e6
  Cyrus Leung authored Dec 15, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  b10609e6
- [torch.compile] allow tracking forward time (#11081) · a1c02058
  youkaichao authored Dec 14, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  a1c02058
- [[Misc]Upgrade bitsandbytes to the latest version 0.45.0 (#11201) · 15859f23
  Jee Jee Li authored Dec 15, 2024
  
  15859f23
14 Dec, 2024 10 commits
- [Performance][Core] Optimize the performance of evictor v1 and v2 by applying... · 88693683
  Sungjae Lee authored Dec 15, 2024
```
[Performance][Core] Optimize the performance of evictor v1 and v2 by applying a priority queue and lazy deletion (#7209)
```
  88693683
- Enable mypy checking on V1 code (#11105) · 6d917d0e
  Mark McLoughlin authored Dec 14, 2024
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  6d917d0e
- [VLM] Fully dynamic prompt replacement in merged input processor (#11199) · 93abf23a
  Cyrus Leung authored Dec 15, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  93abf23a
- [Frontend] Add `logits_processors` as an extra completion argument (#11150) · 9c3dadd1
  Brad Hilton authored Dec 14, 2024
```
Signed-off-by: Brad Hilton <brad.hilton.nw@gmail.com>
```
  9c3dadd1
- [Misc] Minor improvements to the readability of PunicaWrapperBase (#11200) · 3cb57698
  Jee Jee Li authored Dec 15, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  3cb57698
- [V1][Bugfix] Fix V1 TP trust-remote-code (#11182) · ea7bd68d
  Tyler Michael Smith authored Dec 14, 2024
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  ea7bd68d
- [Core] Update outlines and increase its threadpool size (#11140) · 48259264
  Russell Bryant authored Dec 14, 2024
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  48259264
- [Bugfix][V1] Re-compute an entire block when fully cache hit (#11186) · 9855aea2
  Cody Yu authored Dec 13, 2024
```
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
```
  9855aea2
- [V1][Bugfix] Fix EngineCoreProc profile (#11185) · 4b5b8a6a
  Tyler Michael Smith authored Dec 13, 2024
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  4b5b8a6a
- [Core] V1: Use multiprocessing by default (#11074) · 4863e5fb
  Russell Bryant authored Dec 13, 2024
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  4863e5fb
13 Dec, 2024 16 commits
- [Distributed] Allow the placement group more time to wait for resources to be ready (#11138) · 0d8451c3
  Jiaxin Shan authored Dec 13, 2024
```
Signed-off-by: Jiaxin Shan <seedjeffwan@gmail.com>
```
  0d8451c3
- [Bugfix][Hardware][CPU] Enable Gemma2 with SDPA on CPU backend (#11169) · 0a56bcc0
  Jani Monoses authored Dec 13, 2024
  
  0a56bcc0
- [Doc] Reorganize online pooling APIs (#11172) · 0920ab91
  Cyrus Leung authored Dec 14, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  0920ab91
- [Bugfix] using len(tokenizer) instead of tokenizer.vocab_size in... · 5b0ed839
  zhangjf authored Dec 13, 2024
```
[Bugfix] using len(tokenizer) instead of tokenizer.vocab_size in AllowedTokenIdsLogitsProcessor (#11156)
```
  5b0ed839
- [Core] support LoRA and prompt adapter in content-based hashing for Block... · c31d4a57
  Sungjae Lee authored Dec 14, 2024
```
[Core] support LoRA and prompt adapter in content-based hashing for Block Manager v2 prefix caching (#8240)
```
  c31d4a57
- [Refactor]A simple device-related refactor (#11163) · d1fa714c
  Chenguang Li authored Dec 13, 2024
```
Signed-off-by: noemotiovon <noemotiovon@gmail.com>
Co-authored-by: noemotiovon <noemotiovon@gmail.com>
```
  d1fa714c
- [V1][VLM] Fix edge case bug for InternVL2 (#11165) · 969da7d7
  Roger Wang authored Dec 13, 2024
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  969da7d7
- [Frontend] Separate pooling APIs in offline inference (#11129) · eeec9e33
  Cyrus Leung authored Dec 13, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  eeec9e33
- PaliGemma 2 support (#11142) · 7cd74091
  Jani Monoses authored Dec 13, 2024
  
  7cd74091
- [core] clean up cudagraph batchsize padding logic (#10996) · be39e3cd
  youkaichao authored Dec 12, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  be39e3cd
- [Bugfix][V1] Fix 'NoneType' object has no attribute 'hash_value' (#11157) · 34f1a806
  Cody Yu authored Dec 12, 2024
```
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
```
  34f1a806
- [ROCm][AMD] Disable auto enabling chunked prefill on ROCm (#11146) · 00c1bde5
  Gregory Shtrasberg authored Dec 13, 2024
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  00c1bde5
- [Bugfix] Update starcoder2 to remap k/v scale names for kv_cache quantization (#11148) · 3989a798
  Dipika Sikka authored Dec 13, 2024
  
  3989a798
- [Bugfix] Use runner_type instead of task in GritLM (#11144) · 1efce686
  Pooya Davoodi authored Dec 12, 2024
```
Signed-off-by: Pooya Davoodi <pooya.davoodi@parasail.io>
```
  1efce686
- [torch.compile] Dynamic fp8 + rms_norm fusion (#10906) · 30870b4f
  Luka Govedič authored Dec 12, 2024
```
Signed-off-by: luka <luka@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
```
  30870b4f
- [Misc][V1] Fix type in v1 prefix caching (#11151) · 78ed8f57
  Cody Yu authored Dec 12, 2024
  
  78ed8f57
12 Dec, 2024 10 commits
- [Bugfix] Fix value unpack error of simple connector for KVCache transfer. (#11058) · db6c264a
  shangmingc authored Dec 13, 2024
```
Signed-off-by: ShangmingCai <csmthu@gmail.com>
```
  db6c264a
- Fix logging of the vLLM Config (#11143) · 9f3974a3
  Jeremy Arnold authored Dec 12, 2024
  
  9f3974a3
- [Misc] Validate grammar and fail early (#11119) · 2c97eca1
  Cody Yu authored Dec 12, 2024
  
  2c97eca1
- [Bugfix] Quick fix to make Pixtral-HF load correctly again after 39e227c7 . (#11024) · 5d712571
  Jeff Cook authored Dec 12, 2024
  
  5d712571
- [V1] Fix torch profiling for offline inference (#11125) · 4816d20a
  Roger Wang authored Dec 12, 2024
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  4816d20a
- [Misc][LoRA] Ensure Lora Adapter requests return adapter name (#11094) · 85362f02
  Jiaxin Shan authored Dec 12, 2024
```
Signed-off-by: Jiaxin Shan <seedjeffwan@gmail.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  85362f02
- [core][distributed] initialization from StatelessProcessGroup (#10986) · 62de37a3
  youkaichao authored Dec 12, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  62de37a3
- [Hardware][Intel-Gaudi] Enable LoRA support for Intel Gaudi (HPU) (#10565) · 81958242
  Sanju C Sudhakaran authored Dec 12, 2024
```
Signed-off-by: Sanju C Sudhakaran <scsudhakaran@habana.ai>
```
  81958242
- [V1] Use more persistent buffers to optimize input preparation overheads (#11111) · f092153f
  Woosuk Kwon authored Dec 11, 2024
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  f092153f
- [Model] Add support for embedding model GritLM (#10816) · 1da8f0e1
  Pooya Davoodi authored Dec 11, 2024
```
Signed-off-by: Pooya Davoodi <pooya.davoodi@parasail.io>
```
  1da8f0e1