Commits · 0a71900bc92b4a18d5545e9d5dc0ca750add3c69 · OpenDAS / vllm_cscc · GitLab

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
26 Nov, 2024 1 commit

[Bugfix] Fix for Spec model TP + Chunked Prefill (#10232) · db66e018

Murali Andoorveedu authored Nov 26, 2024


Signed-off-by: andoorve <37849411+andoorve@users.noreply.github.com>
Signed-off-by: Sourashis Roy <sroy@roblox.com>
Co-authored-by: Sourashis Roy <sroy@roblox.com>

db66e018

22 Nov, 2024 1 commit
- [torch.compile] support all attention backends (#10558) · eebad39f
  youkaichao authored Nov 22, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  eebad39f
15 Nov, 2024 1 commit
- [Bugfix] Qwen-vl output is inconsistent in speculative decoding (#10350) · 2ec88272
  Sky Lee authored Nov 15, 2024
  
  2ec88272
09 Nov, 2024 1 commit
- [0/N] Rename `MultiModalInputs` to `MultiModalKwargs` (#10040) · e0191a95
  Cyrus Leung authored Nov 09, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  e0191a95
07 Nov, 2024 1 commit
- [Feature] [Spec decode]: Combine chunked prefill with speculative decoding (#9291) · 9d43afcc
  Nicolò Lucchesi authored Nov 07, 2024
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  9d43afcc
06 Nov, 2024 1 commit
- [Bugfix][SpecDecode] kv corruption with bonus tokens in spec decode (#9730) · 0c63c34f
  Sungjae Lee authored Nov 06, 2024
```
Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
```
  0c63c34f
04 Nov, 2024 1 commit
- [4.5/N] bugfix for quant config in speculative decode (#10007) · 2094062b
  youkaichao authored Nov 04, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  2094062b
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
27 Oct, 2024 1 commit
- [Misc] SpecDecodeWorker supports profiling (#9719) · 67a6882d
  科英 authored Oct 27, 2024
```
Signed-off-by: Abatom <abatom@163.com>
```
  67a6882d
21 Oct, 2024 1 commit
- [Doc] Consistent naming of attention backends (#9498) · 496e991d
  Thomas Parnell authored Oct 21, 2024
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  496e991d
16 Oct, 2024 1 commit
- [Performance][Spec Decode] Optimize ngram lookup performance (#9333) · 83450458
  Lily Liu authored Oct 16, 2024
  
  83450458
12 Oct, 2024 1 commit
- [SpecDec] Remove Batch Expansion (2/3) (#9298) · 89feb4c8
  Lily Liu authored Oct 11, 2024
  
  89feb4c8
11 Oct, 2024 1 commit
- [Doc] Compatibility matrix for mutual exclusive features (#8512) · 8baf85e4
  Wallas Henrique authored Oct 11, 2024
```
Signed-off-by: Wallas Santos <wallashss@ibm.com>
```
  8baf85e4
06 Oct, 2024 1 commit
- [Bugfix] Fix try-catch conditions to import correct Flash Attention Backend in Draft Model (#9101) · 23fea871
  TJian authored Oct 05, 2024
  
  23fea871
03 Oct, 2024 1 commit
- [misc] add forward context for attention (#9029) · 9aaf14c6
  youkaichao authored Oct 03, 2024
  
  9aaf14c6
01 Oct, 2024 1 commit
- [Spec Decode] (1/2) Remove batch expansion (#8839) · 15702038
  Lily Liu authored Oct 01, 2024
  
  15702038
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
18 Sep, 2024 1 commit

[CI/Build] Update Ruff version (#8469) · 9d104b5b

Aaron Pham authored Sep 18, 2024


Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

9d104b5b

10 Sep, 2024 1 commit
- [Spec Decode] Move ops.advance_step to flash attn advance_step (#8224) · 5faedf1b
  Kevin Lin authored Sep 10, 2024
  
  5faedf1b
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
29 Aug, 2024 1 commit
- [Bugfix] Unify rank computation across regular decoding and speculative decoding (#7899) · f205c098
  Jonas M. Kübler authored Aug 29, 2024
  
  f205c098
25 Aug, 2024 1 commit
- [Spec Decoding] Streamline batch expansion tensor manipulation (#7851) · 1856aff4
  Nick Hill authored Aug 25, 2024
  
  1856aff4
22 Aug, 2024 2 commits
- [Bugfix] spec decode handle None entries in topk args in create_sequence_group_output (#7232) · cc0eaf12
  Travis Johnson authored Aug 22, 2024
```
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
```
  cc0eaf12
- [Speculative Decoding] EAGLE Implementation with Top-1 proposer (#6830) · a3fce56b
  Abhinav Goyal authored Aug 22, 2024
  
  a3fce56b
20 Aug, 2024 2 commits
- [Core] Add `AttentionState` abstraction (#7663) · 3b682179
  Antoni Baum authored Aug 20, 2024
  
  3b682179
- [Speculative Decoding] Fixing hidden states handling in batch expansion (#7508) · 312f7612
  Abhinav Goyal authored Aug 20, 2024
  
  312f7612
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 1 commit
- [VLM] Refactor `MultiModalConfig` initialization and profiling (#7530) · bbf55c48
  Roger Wang authored Aug 17, 2024
  
  bbf55c48
16 Aug, 2024 1 commit
- [spec decode] [4/N] Move update_flash_attn_metadata to attn backend (#7571) · f366f633
  William Lin authored Aug 16, 2024
```
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
```
  f366f633
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
- [Speculative decoding] [Multi-Step] decouple should_modify_greedy_probs_inplace (#6971) · 57b7be0e
  William Lin authored Aug 08, 2024
  
  57b7be0e
05 Aug, 2024 2 commits
- [SpecDecode] Support FlashInfer in DraftModelRunner (#6926) · e9630458
  Bongwon Jang authored Aug 06, 2024
  
  e9630458
- [Speculative decoding] Add periodic log with time spent in proposal/scoring/verification (#6963) · 82a1b1a8
  Cade Daniel authored Aug 05, 2024
  
  82a1b1a8
31 Jul, 2024 1 commit
- [Bugfix] Fix broadcasting logic for `multi_modal_kwargs` (#6836) · f230cc2c
  Cyrus Leung authored Jul 31, 2024
  
  f230cc2c
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