Commits · da02cb4b274ab8bcebb8b8e677ff4b43440bc499 · OpenDAS / vllm_cscc

18 Jan, 2025 1 commit
- [core] further polish memory profiling (#12126) · da02cb4b
  youkaichao authored Jan 18, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  da02cb4b
16 Jan, 2025 1 commit
- Support torchrun and SPMD-style offline inference (#12071) · bf53e0c7
  youkaichao authored Jan 16, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  bf53e0c7
13 Jan, 2025 1 commit
- [Misc]Minor Changes about Worker (#11555) · c3f05b09
  Chenguang Li authored Jan 13, 2025
```
Signed-off-by: Chenguang Li <757486878@qq.com>
```
  c3f05b09
10 Jan, 2025 1 commit
- [torch.compile] Hide KV cache behind torch.compile boundary (#11677) · cf5f000d
  Chen Zhang authored Jan 10, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  cf5f000d
16 Dec, 2024 1 commit
- [core] overhaul memory profiling and fix backward compatibility (#10511) · 551603fe
  youkaichao authored Dec 16, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  551603fe
11 Dec, 2024 2 commits
- [Doc] Update docs to refer to pooling models (#11093) · cad5c0a6
  Cyrus Leung authored Dec 11, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  cad5c0a6
- [Misc] Split up pooling tasks (#10820) · 8f10d5e3
  Cyrus Leung authored Dec 11, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  8f10d5e3
02 Dec, 2024 1 commit

[Core] Implement disagg prefill by StatelessProcessGroup (#10502) · 0590ec3f

Kuntai Du authored Dec 01, 2024



This PR provides initial support for single-node disaggregated prefill in 1P1D scenario.
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
Co-authored-by: ApostaC <yihua98@uchicago.edu>
Co-authored-by: YaoJiayi <120040070@link.cuhk.edu.cn>

0590ec3f

01 Dec, 2024 1 commit
- [Misc] Rename embedding classes to pooling (#10801) · d2f058e7
  Cyrus Leung authored Dec 01, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  d2f058e7
27 Nov, 2024 1 commit
- Remove hard-dependencies of Speculative decode to CUDA workers (#10587) · 0a71900b
  Chendi.Xue authored Nov 26, 2024
```
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
```
  0a71900b
20 Nov, 2024 1 commit
- [7/N] torch.compile, reduce compilation time (#10460) · 0cd3d971
  youkaichao authored Nov 20, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  0cd3d971
15 Nov, 2024 1 commit
- [Bugfix] Fix fully sharded LoRA bug (#10352) · 1d65ec7e
  Jee Jee Li authored Nov 15, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  1d65ec7e
07 Nov, 2024 1 commit
- [Misc] Consolidate ModelConfig code related to HF config (#10104) · db7db4aa
  Cyrus Leung authored Nov 07, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  db7db4aa
02 Nov, 2024 1 commit
- [2/N] executor pass the complete config to worker/modelrunner (#9938) · e8937954
  youkaichao authored Nov 02, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  e8937954
19 Oct, 2024 1 commit
- 🐛 fix torch memory profiling (#9516) · 380e1863
  Joe Runde authored Oct 18, 2024
```
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
```
  380e1863
18 Oct, 2024 2 commits
- [Model] Add user-configurable task for models that support both generation and embedding (#9424) · 051eaf6d
  Cyrus Leung authored Oct 19, 2024
  
  051eaf6d
- [Bugfix][Core] Use torch.cuda.memory_stats() to profile peak memory usage (#9352) · de4008e2
  Joe Runde authored Oct 17, 2024
```
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
```
  de4008e2
11 Oct, 2024 1 commit
- [Model] Support Mamba (#6484) · 7342a7d7
  Tyler Michael Smith authored Oct 11, 2024
  
  7342a7d7
18 Sep, 2024 1 commit
- [CI/Build] Avoid CUDA initialization (#8534) · 6ffa3f31
  Cyrus Leung authored Sep 18, 2024
  
  6ffa3f31
11 Sep, 2024 1 commit
- [Kernel][Misc] register ops to prevent graph breaks (#6917) · 73202dbe
  bnellnm authored Sep 11, 2024
```
Co-authored-by: Sage Moore <sage@neuralmagic.com>
```
  73202dbe
30 Aug, 2024 1 commit
- [Core] Logprobs support in Multi-step (#7652) · 428dd144
  afeldman-nm authored Aug 29, 2024
  
  428dd144
22 Aug, 2024 1 commit
- [Speculative Decoding] EAGLE Implementation with Top-1 proposer (#6830) · a3fce56b
  Abhinav Goyal authored Aug 22, 2024
  
  a3fce56b
21 Aug, 2024 1 commit
- [misc] Add Torch profiler support (#7451) · dd53c4b0
  William Lin authored Aug 21, 2024
```
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
```
  dd53c4b0
19 Aug, 2024 1 commit
- [Core] Optimize SPMD architecture with delta + serialization optimization (#7109) · ff7ec82c
  SangBin Cho authored Aug 18, 2024
  
  ff7ec82c
17 Aug, 2024 2 commits
- [VLM] Refactor `MultiModalConfig` initialization and profiling (#7530) · bbf55c48
  Roger Wang authored Aug 17, 2024
  
  bbf55c48
- [misc] use nvml to get consistent device name (#7582) · eed020f6
  youkaichao authored Aug 16, 2024
  
  eed020f6
11 Aug, 2024 1 commit
- [core] [2/N] refactor worker_base input preparation for multi-step (#7387) · c08e2b30
  William Lin authored Aug 11, 2024
  
  c08e2b30
09 Aug, 2024 2 commits
- [Core] Add span metrics for model_forward, scheduler and sampler time (#7089) · 933790c2
  Mahesh Keralapura authored Aug 09, 2024
  
  933790c2
- [Core] Support serving encoder/decoder models (#7258) · 7eb4a51c
  Cyrus Leung authored Aug 09, 2024
  
  7eb4a51c
06 Aug, 2024 1 commit

[Core] Subclass ModelRunner to support cross-attention & encoder sequences... · fd95e026

afeldman-nm authored Aug 06, 2024


[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942)
Co-authored-by: Andrew Feldman <afeld2012@gmail.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>

fd95e026

02 Aug, 2024 1 commit
- [ci] set timeout for test_oot_registration.py (#7082) · 80694951
  youkaichao authored Aug 02, 2024
  
  80694951
17 Jul, 2024 1 commit
- [Misc] Use `torch.Tensor` for type annotation (#6505) · a9a2e74d
  Woosuk Kwon authored Jul 17, 2024
  
  a9a2e74d
10 Jul, 2024 1 commit
- [Speculative Decoding] Medusa Implementation with Top-1 proposer (#4978) · 2416b26e
  Abhinav Goyal authored Jul 10, 2024
  
  2416b26e
09 Jul, 2024 1 commit

[CORE] Adding support for insertion of soft-tuned prompts (#4645) · 4d6ada94

Swapnil Parekh authored Jul 09, 2024


Co-authored-by: Swapnil Parekh <swapnilp@ibm.com>
Co-authored-by: Joe G <joseph.granados@h2o.ai>
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>

4d6ada94

03 Jul, 2024 3 commits
- [core][distributed] support n layers % pp size != 0 (#6115) · 3de6e6a3
  youkaichao authored Jul 03, 2024
  
  3de6e6a3
- [vlm] Remove vision language config. (#6089) · d9e98f42
  xwjiang2010 authored Jul 03, 2024
```
Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
```
  d9e98f42
- [hardware][misc] introduce platform abstraction (#6080) · 482045ee
  youkaichao authored Jul 02, 2024
  
  482045ee
02 Jul, 2024 1 commit
- [Core] Pipeline Parallel Support (#4412) · c5832d2a
  Murali Andoorveedu authored Jul 02, 2024
```
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
```
  c5832d2a
01 Jul, 2024 1 commit
- [misc][cuda] use nvml to avoid accidentally cuda initialization (#6007) · 614aa512
  youkaichao authored Jun 30, 2024
  
  614aa512
28 Jun, 2024 1 commit
- [Spec Decode] Introduce DraftModelRunner (#5799) · b2c62023
  Cody Yu authored Jun 28, 2024
  
  b2c62023