Commits · 4e06836d059c422753947deba4100c26a18e1223 · OpenDAS / vllm_cscc · GitLab

"vllm/v1/executor/ray_utils.py" did not exist on "65b89d16ee54063d0737e3da1b15e2177916118d"

18 Nov, 2024 1 commit
- [fix]修复test_spec_decode_worker中的错误 · dc2ce261
  王敏 authored Nov 18, 2024
  
  dc2ce261
06 Nov, 2024 1 commit

1.解决medusa模型多卡推理结果异常问题 · f9060e6b

王敏 authored Nov 06, 2024

2.examples中添加medusa readme
3.修复model_runner中input_positions配置错误的笔误，解决多个模型运行失败问题

f9060e6b

24 Oct, 2024 1 commit
- 增加medusa并行解码功能,后续增加使用说明和测试文档 · 19bc93d9
  王敏 authored Oct 24, 2024
  
  19bc93d9
25 Sep, 2024 1 commit
- [Core][Bugfix] Support prompt_logprobs returned with speculative decoding (#8047) · 01b6f9e1
  Travis Johnson authored Sep 24, 2024
```
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
```
  01b6f9e1
22 Sep, 2024 1 commit
- [SpecDec][Misc] Cleanup, remove bonus token logic. (#8701) · c6bd70d7
  Lily Liu authored Sep 22, 2024
  
  c6bd70d7
02 Sep, 2024 1 commit
- [SpecDecode][Kernel] Flashinfer Rejection Sampling (#7244) · e6a26ed0
  Lily Liu authored Sep 01, 2024
  
  e6a26ed0
30 Aug, 2024 1 commit
- [Core] Logprobs support in Multi-step (#7652) · 428dd144
  afeldman-nm authored Aug 29, 2024
  
  428dd144
25 Aug, 2024 1 commit
- [Spec Decoding] Streamline batch expansion tensor manipulation (#7851) · 1856aff4
  Nick Hill authored Aug 25, 2024
  
  1856aff4
22 Aug, 2024 1 commit
- [Speculative Decoding] EAGLE Implementation with Top-1 proposer (#6830) · a3fce56b
  Abhinav Goyal authored Aug 22, 2024
  
  a3fce56b
20 Aug, 2024 1 commit
- [Speculative Decoding] Fixing hidden states handling in batch expansion (#7508) · 312f7612
  Abhinav Goyal authored Aug 20, 2024
  
  312f7612
09 Aug, 2024 1 commit
- [Speculative decoding] [Multi-Step] decouple should_modify_greedy_probs_inplace (#6971) · 57b7be0e
  William Lin authored Aug 08, 2024
  
  57b7be0e
05 Aug, 2024 1 commit
- [Speculative decoding] Add periodic log with time spent in proposal/scoring/verification (#6963) · 82a1b1a8
  Cade Daniel authored Aug 05, 2024
  
  82a1b1a8
30 Jul, 2024 1 commit
- [BugFix] Fix use of per-request seed with pipeline parallel (#6698) · 5cf9254a
  Nick Hill authored Jul 30, 2024
  
  5cf9254a
24 Jul, 2024 1 commit
- [Bugfix] Miscalculated latency lead to time_to_first_token_seconds inaccurate. (#6686) · 40468b13
  Allen.Dou authored Jul 24, 2024
  
  40468b13
21 Jul, 2024 1 commit
- [Spec Decode] Disable Log Prob serialization to CPU for spec decoding for both... · 14f91fe6
  sroy745 authored Jul 20, 2024
```
[Spec Decode] Disable Log Prob serialization to CPU for spec decoding for both draft and target models. (#6485)
```
  14f91fe6
19 Jul, 2024 2 commits
- [BUGFIX] Raise an error for no draft token case when draft_tp>1 (#6369) · a921e863
  Woo-Yeon Lee authored Jul 19, 2024
  
  a921e863
- [Bugfix] Make spec. decode respect per-request seed. (#6034) · d4201e06
  Thomas Parnell authored Jul 19, 2024
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
```
  d4201e06
17 Jul, 2024 1 commit
- [Misc][Speculative decoding] Typos and typing fixes (#6467) · a19e8d37
  shangmingc authored Jul 17, 2024
```
Co-authored-by: caishangming.csm <caishangming.csm@alibaba-inc.com>
```
  a19e8d37
10 Jul, 2024 2 commits
- [Speculative Decoding] Enabling bonus token in speculative decoding for KV... · ae151d73
  sroy745 authored Jul 10, 2024
```
[Speculative Decoding] Enabling bonus token in speculative decoding for KV cache based models (#5765)
```
  ae151d73
- [Speculative Decoding] Medusa Implementation with Top-1 proposer (#4978) · 2416b26e
  Abhinav Goyal authored Jul 10, 2024
  
  2416b26e
02 Jul, 2024 1 commit
- [Speculative Decoding] MLPSpeculator Tensor Parallel support (1/2) (#6050) · 15aba081
  Sirej Dua authored Jul 02, 2024
```
Co-authored-by: Sirej Dua <sirej.dua@databricks.com>
Co-authored-by: Sirej Dua <Sirej Dua>
```
  15aba081
01 Jul, 2024 1 commit
- [Speculative Decoding 2/2 ] Integrate typical acceptance sampler into Spec Decode Worker (#5348) · 80ca1e6a
  sroy745 authored Jul 01, 2024
  
  80ca1e6a
28 Jun, 2024 1 commit
- [Spec Decode] Introduce DraftModelRunner (#5799) · b2c62023
  Cody Yu authored Jun 28, 2024
  
  b2c62023
25 Jun, 2024 1 commit
- [Speculative Decoding] Support draft model on different tensor-parallel size... · 2ce5d668
  Woo-Yeon Lee authored Jun 25, 2024
```
 [Speculative Decoding] Support draft model on different tensor-parallel size than target model (#5414)
```
  2ce5d668
21 Jun, 2024 1 commit

[Model] MLPSpeculator speculative decoding support (#4947) · b12518d3

Joshua Rosenkranz authored Jun 20, 2024


Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: Davis Wertheimer <Davis.Wertheimer@ibm.com>

b12518d3

15 Jun, 2024 1 commit
- [mypy] Enable type checking for test directory (#5017) · 0e9164b4
  Cyrus Leung authored Jun 15, 2024
  
  0e9164b4
11 Jun, 2024 1 commit
- [Misc] Various simplifications and typing fixes (#5368) · a0086298
  Nick Hill authored Jun 10, 2024
  
  a0086298
05 Jun, 2024 1 commit
- [Speculative Decoding] Add `ProposerWorkerBase` abstract class (#5252) · faf71bcd
  Nick Hill authored Jun 05, 2024
  
  faf71bcd
25 May, 2024 1 commit
- [Dynamic Spec Decoding] Minor fix for disabling speculative decoding (#5000) · d5a16977
  Lily Liu authored May 25, 2024
  
  d5a16977
22 May, 2024 1 commit
- [Core] Eliminate parallel worker per-step task scheduling overhead (#4894) · eb6d3c26
  Nick Hill authored May 22, 2024
  
  eb6d3c26
16 May, 2024 1 commit
- [Speculative decoding][Re-take] Enable TP>1 speculative decoding (#4840) · 973617ae
  Cody Yu authored May 16, 2024
```
Co-authored-by: Cade Daniel <edacih@gmail.com>
Co-authored-by: Cade Daniel <cade@anyscale.com>
```
  973617ae
08 May, 2024 1 commit
- [Dynamic Spec Decoding] Auto-disable by the running queue size (#4592) · f942efb5
  Cody Yu authored May 08, 2024
```
Co-authored-by: Cade Daniel <edacih@gmail.com>
```
  f942efb5
07 May, 2024 1 commit

[Bug fix][Core] fixup ngram not setup correctly (#4551) · 8344f774

leiwen83 authored May 08, 2024


Co-authored-by: Lei Wen <wenlei03@qiyi.com>
Co-authored-by: Cade Daniel <edacih@gmail.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>

8344f774

04 May, 2024 1 commit
- [Misc][Refactor] Introduce ExecuteModelData (#4540) · bc8ad684
  Cody Yu authored May 03, 2024
  
  bc8ad684
03 May, 2024 1 commit
- [Speculative decoding] Support target-model logprobs (#4378) · ab502751
  Cade Daniel authored May 03, 2024
  
  ab502751
01 May, 2024 1 commit
- [Speculative decoding] Add ngram prompt lookup decoding (#4237) · b38e42fb
  leiwen83 authored May 02, 2024
```
Co-authored-by: Lei Wen <wenlei03@qiyi.com>
```
  b38e42fb
26 Apr, 2024 1 commit
- [CI] Disable non-lazy string operation on logging (#4326) · a88081bf
  SangBin Cho authored Apr 26, 2024
```
Co-authored-by: Danny Guinther <dguinther@neuralmagic.com>
```
  a88081bf
23 Apr, 2024 1 commit
- [Speculative decoding 7/9] Speculative decoding end-to-end correctness tests. (#3951) · 62b8aebc
  Cade Daniel authored Apr 23, 2024
  
  62b8aebc
18 Apr, 2024 1 commit
- [Typing] Mypy typing part 2 (#4043) · 533d2a1f
  SangBin Cho authored Apr 18, 2024
```
Co-authored-by: SangBin Cho <sangcho@sangcho-LT93GQWG9C.local>
```
  533d2a1f
16 Apr, 2024 1 commit
- [Speculative decoding 6/9] Integrate speculative decoding with LLMEngine (#3894) · e95cd879
  Cade Daniel authored Apr 16, 2024
  
  e95cd879