Commits · 4d31cd424bdd5935cefa8f03e137bba127be31dd · OpenDAS / vllm_cscc · GitLab

14 Oct, 2024 4 commits
- [Frontend] merge beam search implementations (#9296) · 4d31cd42
  Brendan Wong authored Oct 14, 2024
  
  4d31cd42
- [TPU] Fix TPU SMEM OOM by Pallas paged attention kernel (#9350) · 473e7b36
  Woosuk Kwon authored Oct 14, 2024
  
  473e7b36
- [Hardware][intel GPU] add async output process for xpu (#8897) · 4141608c
  Kunshang Ji authored Oct 15, 2024
  
  4141608c
- [Model] Molmo vLLM Integration (#9016) · dfe43a20
  Reza Salehi authored Oct 14, 2024
```
Co-authored-by: sanghol <sanghol@allenai.org>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
```
  dfe43a20
13 Oct, 2024 2 commits
- [Bugfix] Bandaid fix for speculative decoding tests (#9327) · 16b24e7d
  Tyler Michael Smith authored Oct 13, 2024
  
  16b24e7d
- [CI] Fix merge conflict (#9317) · f519902c
  Lily Liu authored Oct 12, 2024
  
  f519902c
12 Oct, 2024 5 commits
- [Bugfix]Fix MiniCPM's LoRA bug (#9286) · 250e26a6
  Jee Jee Li authored Oct 13, 2024
  
  250e26a6
- [Bugfix] Fix bug of xformer prefill for encoder-decoder (#9026) · 00298e09
  Xiang Xu authored Oct 12, 2024
  
  00298e09
- [SpecDec] Remove Batch Expansion (2/3) (#9298) · 89feb4c8
  Lily Liu authored Oct 11, 2024
  
  89feb4c8
- [BugFix] Fix tool call finish reason in streaming case (#9209) · ec10cb85
  Maximilien de Bayser authored Oct 11, 2024
```
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
```
  ec10cb85
- [bugfix] fix f-string for error (#9295) · d11b46f3
  Prashant Gupta authored Oct 11, 2024
```
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
```
  d11b46f3
11 Oct, 2024 10 commits
- [Bugfix] Sets `is_first_step_output` for TPUModelRunner (#9202) · c6cf9295
  Allen Wang authored Oct 11, 2024
  
  c6cf9295
- [Doc] Compatibility matrix for mutual exclusive features (#8512) · 8baf85e4
  Wallas Henrique authored Oct 11, 2024
```
Signed-off-by: Wallas Santos <wallashss@ibm.com>
```
  8baf85e4
- [Doc] Remove outdated comment to avoid misunderstanding (#9287) · 1a182387
  homeffjy authored Oct 12, 2024
  
  1a182387
- [Model] Add GLM-4v support and meet vllm==0.6.2 (#9242) · 6cf1167c
  sixgod authored Oct 12, 2024
  
  6cf1167c
- [Kernel] adding fused moe kernel config for L40S TP4 (#9245) · f710090d
  Burkhard Ringlein authored Oct 11, 2024
  
  f710090d
- [Model] Support Mamba (#6484) · 7342a7d7
  Tyler Michael Smith authored Oct 11, 2024
  
  7342a7d7
- [Bugfix] Fix priority in multiprocessing engine (#9277) · df3dcdf4
  Sebastian Schoennenbeck authored Oct 11, 2024
  
  df3dcdf4
- [Misc][LoRA] Support loading LoRA weights for target_modules in reg format (#9275) · 36ea7907
  Jee Jee Li authored Oct 11, 2024
  
  36ea7907
- [Misc] Collect model support info in a single process per model (#9233) · e808156f
  Cyrus Leung authored Oct 11, 2024
  
  e808156f
- [misc] hide best_of from engine (#9261) · cbc2ef55
  youkaichao authored Oct 10, 2024
```
Co-authored-by: Brendan Wong <bjwpokemon@gmail.com>
```
  cbc2ef55
10 Oct, 2024 7 commits
- [torch.compile] generic decorators (#9258) · e00c094f
  youkaichao authored Oct 10, 2024
  
  e00c094f
- [torch.compile] integration with compilation control (#9058) · e4d652ea
  youkaichao authored Oct 10, 2024
  
  e4d652ea
- [Model] support input image embedding for minicpmv (#9237) · 04de9057
  whyiug authored Oct 10, 2024
  
  04de9057
- [Bugfix] Fix lm_head weights tying with lora for llama (#9227) · 07c11cf4
  Isotr0py authored Oct 10, 2024
  
  07c11cf4
- [Core] Add an environment variable which needs to be set explicitly to allow... · f3a507f1
  sroy745 authored Oct 09, 2024
```
[Core] Add an environment variable which needs to be set explicitly to allow BlockSpaceManagerV1 (#9149)
```
  f3a507f1
- [misc] improve model support check in another process (#9208) · de895f16
  youkaichao authored Oct 09, 2024
  
  de895f16
- [Core] Fix invalid args to _process_request (#9201) · cf25b93b
  Russell Bryant authored Oct 10, 2024
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  cf25b93b
09 Oct, 2024 10 commits
- [CI/Build] mypy: check vllm/entrypoints (#9194) · cdca8994
  Russell Bryant authored Oct 09, 2024
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  cdca8994
- [Hardware][CPU] Support AWQ for CPU backend (#7515) · ca77dd7a
  Li, Jiang authored Oct 10, 2024
  
  ca77dd7a
- [Bugfix] Access `get_vocab` instead of `vocab` in tool parsers (#9188) · cfaa6008
  Cyrus Leung authored Oct 09, 2024
  
  cfaa6008
- [Bugfix] Fix lora loading for Compressed Tensors in #9120 (#9179) · 21906a6f
  Ahmad Fahadh Ilyas authored Oct 09, 2024
  
  21906a6f
- [ci][test] use load dummy for testing (#9165) · c8627cd4
  youkaichao authored Oct 09, 2024
  
  c8627cd4
- [Bugfix] fix composite weight loading and EAGLE weight loading (#9160) · 8bfaa4e3
  Cyrus Leung authored Oct 09, 2024
  
  8bfaa4e3
- [Frontend] Log the maximum supported concurrency (#8831) · 0b5b5d76
  AlpinDale authored Oct 09, 2024
  
  0b5b5d76
- [Model] Remap FP8 kv_scale in CommandR and DBRX (#9174) · cdc72e3c
  Hui Liu authored Oct 08, 2024
  
  cdc72e3c
- [Misc] Improve validation errors around best_of and n (#9167) · 480b7f40
  Travis Johnson authored Oct 08, 2024
```
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
```
  480b7f40
- support bitsandbytes quantization with more models (#9148) · 2f4117c3
  chenqianfzh authored Oct 08, 2024
  
  2f4117c3
08 Oct, 2024 2 commits
- mypy: check additional directories (#9162) · 2a131965
  Russell Bryant authored Oct 08, 2024
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  2a131965
- [Bugfix] Try to handle older versions of pytorch (#9086) · bd37b9fb
  bnellnm authored Oct 08, 2024
  
  bd37b9fb