Commits · 96e0c9cbbd65ad0b8ad20611b90bcc86a8559aae · OpenDAS / vllm_cscc

01 Nov, 2024 1 commit
- [torch.compile] directly register custom op (#9896) · 96e0c9cb
  youkaichao authored Oct 31, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  96e0c9cb
30 Oct, 2024 2 commits
- [Bugfix] Fix multi nodes TP+PP for XPU (#8884) · 04a3ae0a
  Yan Ma authored Oct 30, 2024
```
Signed-off-by: YiSheng5 <syhm@mail.ustc.edu.cn>
Signed-off-by: yan ma <yan.ma@intel.com>
Co-authored-by: YiSheng5 <syhm@mail.ustc.edu.cn>
```
  04a3ae0a
- [core][distributed] fix custom allreduce in pytorch 2.5 (#9815) · 1ab6f6b4
  youkaichao authored Oct 29, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  1ab6f6b4
24 Oct, 2024 1 commit
- [torch.compile] expanding support and fix allgather compilation (#9637) · ad6f7805
  Yongzao authored Oct 24, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  ad6f7805
22 Oct, 2024 1 commit
- [Hardware][CPU] using current_platform.is_cpu (#9536) · 3ddbe255
  wangshuai09 authored Oct 22, 2024
  
  3ddbe255
18 Oct, 2024 1 commit
- [MISC] Consolidate cleanup() and refactor offline_inference_with_prefix.py (#9510) · d11bf435
  Cody Yu authored Oct 18, 2024
  
  d11bf435
04 Oct, 2024 1 commit
- [torch.compile] improve allreduce registration (#9061) · 663874e0
  youkaichao authored Oct 04, 2024
  
  663874e0
27 Sep, 2024 1 commit
- [misc][distributed] add VLLM_SKIP_P2P_CHECK flag (#8911) · 18e60d7d
  youkaichao authored Sep 27, 2024
  
  18e60d7d
23 Sep, 2024 1 commit
- [Core] Allow IPv6 in VLLM_HOST_IP with zmq (#8575) · b05f5c92
  Russell Bryant authored Sep 23, 2024
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  b05f5c92
21 Sep, 2024 1 commit
- [MISC] add support custom_op check (#8557) · d4bf085a
  Kunshang Ji authored Sep 21, 2024
```
Co-authored-by: youkaichao <youkaichao@126.com>
```
  d4bf085a
18 Sep, 2024 2 commits
- [Core] zmq: bind only to 127.0.0.1 for local-only usage (#8543) · d65798f7
  Russell Bryant authored Sep 18, 2024
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  d65798f7
- [CI/Build] Avoid CUDA initialization (#8534) · 6ffa3f31
  Cyrus Leung authored Sep 18, 2024
  
  6ffa3f31
17 Sep, 2024 1 commit
- [torch.compile] register allreduce operations as custom ops (#8526) · 99aa4edd
  youkaichao authored Sep 16, 2024
  
  99aa4edd
30 Aug, 2024 1 commit
- [TPU] Support single and multi-host TPUs on GKE (#7613) · 2148441f
  Richard Liu authored Aug 30, 2024
  
  2148441f
26 Aug, 2024 1 commit
- [misc] fix custom allreduce p2p cache file generation (#7853) · 05826c88
  youkaichao authored Aug 26, 2024
  
  05826c88
17 Aug, 2024 2 commits
- [core][misc] update libcudart finding (#7620) · d95cc0a5
  youkaichao authored Aug 16, 2024
```
Co-authored-by: cjackal <44624812+cjackal@users.noreply.github.com>
```
  d95cc0a5
- [Bugfix] Fix custom_ar support check (#7617) · e6803499
  bnellnm authored Aug 16, 2024
  
  e6803499
14 Aug, 2024 1 commit
- [Bugfix][CI] Import ray under guard (#7486) · 59edd0f1
  Woosuk Kwon authored Aug 13, 2024
  
  59edd0f1
13 Aug, 2024 2 commits
- [TPU] Support multi-host inference (#7457) · a08df832
  Woosuk Kwon authored Aug 13, 2024
  
  a08df832
- [Bugfix] Fix weight loading for Chameleon when TP>1 (#7410) · 7025b11d
  Cyrus Leung authored Aug 13, 2024
  
  7025b11d
07 Aug, 2024 1 commit
- [distributed][misc] add specialized method for cuda platform (#7249) · 639159b2
  youkaichao authored Aug 07, 2024
  
  639159b2
05 Aug, 2024 1 commit
- [Misc] Fix typo in GroupCoordinator.recv() (#7167) · 997cf783
  Rui Qiao authored Aug 05, 2024
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  997cf783
04 Aug, 2024 1 commit
- [misc][distributed] improve libcudart.so finding (#7127) · 16a1cc9b
  youkaichao authored Aug 04, 2024
  
  16a1cc9b
01 Aug, 2024 1 commit
- PP comm optimization: replace send with partial send + allgather (#6695) · 0437492e
  Aurick Qiao authored Jul 31, 2024
```
Co-authored-by: Aurick Qiao <aurick.qiao@snowflake.com>
```
  0437492e
31 Jul, 2024 2 commits
- [MISC] Introduce pipeline parallelism partition strategies (#6920) · bd700134
  Cody Yu authored Jul 31, 2024
```
Co-authored-by: youkaichao <youkaichao@126.com>
```
  bd700134
- [Bugfix] Fix broadcasting logic for `multi_modal_kwargs` (#6836) · f230cc2c
  Cyrus Leung authored Jul 31, 2024
  
  f230cc2c
27 Jul, 2024 2 commits
- [TPU] Reduce compilation time & Upgrade PyTorch XLA version (#6856) · fad5576c
  Woosuk Kwon authored Jul 27, 2024
  
  fad5576c
- [TPU] Support collective communications in XLA devices (#6813) · d09b94ca
  Woosuk Kwon authored Jul 26, 2024
  
  d09b94ca
26 Jul, 2024 1 commit
- [Hardware] [Intel] Enable Multiprocessing and tensor parallel in CPU backend... · 3bbb4936
  Li, Jiang authored Jul 27, 2024
```
[Hardware] [Intel] Enable Multiprocessing and tensor parallel in CPU backend and update documentation  (#6125)
```
  3bbb4936
25 Jul, 2024 2 commits
- [Bugfix] Add synchronize to prevent possible data race (#6788) · 95db75de
  Tyler Michael Smith authored Jul 25, 2024
```
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
```
  95db75de
- [core][distributed] fix zmq hang (#6759) · 740374d4
  youkaichao authored Jul 24, 2024
  
  740374d4
21 Jul, 2024 1 commit
- [Misc] Remove abused noqa (#6619) · b6df37f9
  Woosuk Kwon authored Jul 21, 2024
  
  b6df37f9
19 Jul, 2024 1 commit
- [bugfix][distributed] fix multi-node bug for shared memory (#6597) · 07eb6f19
  youkaichao authored Jul 19, 2024
  
  07eb6f19
18 Jul, 2024 1 commit
- [BugFix] Avoid secondary error in ShmRingBuffer destructor (#6530) · d25877dd
  Nick Hill authored Jul 17, 2024
  
  d25877dd
17 Jul, 2024 1 commit
- [misc][distributed] improve tests (#6488) · 7f62077a
  youkaichao authored Jul 16, 2024
  
  7f62077a
16 Jul, 2024 1 commit
- [CI/Build] vLLM cache directory for images (#6444) · d9701151
  Cyrus Leung authored Jul 16, 2024
  
  d9701151
12 Jul, 2024 1 commit
- [distributed][misc] be consistent with pytorch for libcudart.so (#6346) · 2b0fb534
  youkaichao authored Jul 11, 2024
```
[distributed][misc] keep consistent with how pytorch finds libcudart.so (#6346)
```
  2b0fb534
10 Jul, 2024 1 commit
- [core][distributed] zmq fallback for broadcasting large objects (#6183) · da78caec
  youkaichao authored Jul 09, 2024
```
[core][distributed] add zmq fallback for broadcasting large objects (#6183)
```
  da78caec
03 Jul, 2024 2 commits
- [core][distributed] support n layers % pp size != 0 (#6115) · 3de6e6a3
  youkaichao authored Jul 03, 2024
  
  3de6e6a3
- [core][distributed] custom allreduce when pp size > 1 (#6117) · 3c6325f0
  youkaichao authored Jul 03, 2024
  
  3c6325f0