Commits · 754b699cbe5eded4525c0eb3e301a17b06d50162 · OpenDAS / vllm_cscc

14 May, 2025 7 commits
- [Bug]: Fix S3 model/tokenizer path resolution (#18083) · 754b699c
  Jon Gill authored May 13, 2025
```
Signed-off-by: Jon Gill <jon@yurts.ai>
```
  754b699c
- [Misc] Remove unused numpy tensor (#18084) · 6e27c6d8
  Roger Wang authored May 13, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.me>
```
  6e27c6d8
- [P/D] Add some more debug logs to `NixlConnector` (#18102) · d5af47a1
  Nick Hill authored May 13, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  d5af47a1
- [Hardware/NVIDIA/Modelopt] Fix modelopt forward method for v1 torch.compile (#18101) · 65f0f74b
  Pavani Majety authored May 13, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  65f0f74b
- [Fix] Support CUDAGraph capture for encoder-decoder on ROCm (#18104) · 176a95c6
  Luka Govedič authored May 13, 2025
```
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
```
  176a95c6
- [v1][KVCacheManager] pass num_new_computed_tokens to kv cache manager (#18001) · f2ae883b
  Chen Zhang authored May 14, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  f2ae883b
- [FEAT] [ROCm]: Add AITER Block-Scaled GEMM Feature (#14968) · 40de1ef4
  vllmellm authored May 14, 2025
```
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  40de1ef4
13 May, 2025 20 commits
- [V1] DP scale-out (2/N): Decouple engine process management and comms (#15977) · 55aa7af9
  Nick Hill authored May 13, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  55aa7af9
- Update deprecated type hinting in `vllm/adapter_commons` (#18073) · 0b217da6
  Harry Mellor authored May 13, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  0b217da6
- Update deprecated type hinting in `vllm/compilation` (#18072) · 19324d66
  Harry Mellor authored May 13, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  19324d66
- [Bugfix] Fix entrypoints metrics tests (#18063) · b922c2eb
  Cyrus Leung authored May 13, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  b922c2eb
- Update deprecated type hinting in `vllm/transformers_utils` (#18058) · 8c946cec
  Harry Mellor authored May 13, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  8c946cec
- Update deprecated type hinting in `vllm/profiler` (#18057) · ff334ca1
  Harry Mellor authored May 13, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  ff334ca1
- Update deprecated type hinting in `model_executor/layers` (#18056) · 6223dd81
  Harry Mellor authored May 13, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  6223dd81
- [Fix] check to make sure processor has chat templates (#18047) · cb528d05
  Aaron Pham authored May 13, 2025
```
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
```
  cb528d05
- [Bugfix] Fix marlin moe fallback logic for llama4 (#18042) · ea6ae8cb
  Michael Goin authored May 13, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  ea6ae8cb
- [BugFix] Set default random seed to 0 for V1 (#17929) · 2ff297dc
  Woosuk Kwon authored May 13, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  2ff297dc
- [Bugfix][V1] Only get input embeddings w/ multi-modal models if first PP (#17916) · 8dd0671b
  Jin Huang authored May 13, 2025
```
Signed-off-by: Jin Huang <jinhun@amazon.com>
Co-authored-by: Jin Huang <jinhun@amazon.com>
```
  8dd0671b
- [v1][KVCacheManager] Avoid full cache hit by controlling max_length (#17999) · f0d610a8
  Chen Zhang authored May 13, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  f0d610a8
- cleanup invalid prints (#18050) · 48545728
  Calvin Chen authored May 13, 2025
```
Signed-off-by: calvin chen <120380290@qq.com>
```
  48545728
- [Feature][V1] Support `tool_choice: required` when using Xgrammar as the... · dc1a8217
  Chauncey authored May 13, 2025
```
[Feature][V1]  Support `tool_choice: required` when using Xgrammar as the `StructuredOutputBackend`. (#17845)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  dc1a8217
- [Bugfix] Avoid repeatedly creating dummy data during engine startup (#17935) · 61e0a506
  Cyrus Leung authored May 13, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  61e0a506
- [Bugfix] Fixes for new marlin moe usage (#18017) · 1df491c5
  Michael Goin authored May 12, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  1df491c5
- [Misc] Slight spelling modification (#18039) · c06af9a9
  Jee Jee Li authored May 13, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  c06af9a9
- Implements dual-chunk-flash-attn backend for dual chunk attention with sparse... · 60f76243
  Tao He authored May 13, 2025
```
Implements dual-chunk-flash-attn backend for dual chunk attention with sparse attention support (#11844)
```
  60f76243
- Remove noisy warnings from `SchedulerConfig` (#17995) · d67085c2
  Harry Mellor authored May 13, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  d67085c2
- Use NVFP4 Marlin for CompressedTensorsW4A16Fp4 (#18000) · 307939f2
  Michael Goin authored May 12, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Dipika <dipikasikka1@gmail.com>
Co-authored-by: Dipika <dipikasikka1@gmail.com>
```
  307939f2
12 May, 2025 13 commits

Update some more deprecated type hinting (#17998) · 9d7ea9db
Harry Mellor authored May 13, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
9d7ea9db

[Model] Support MiMo-7B inference with MTP (#17433) · acee8f48

bwshen-mi authored May 13, 2025


Signed-off-by: wp-alpha <wangpeng66@xiaomi.com>
Co-authored-by: wangpeng66 <wangpeng66@xiaomi.com>

acee8f48

Fix FBGEMM integration (#18002) · f065de4e
Michael Goin authored May 12, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
f065de4e
[V1][Spec Decode] Eagle unit tests (#17350) · dc990536
wwl2755 authored May 12, 2025
```
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
```
dc990536
[Chore] Remove unused method (#18024) · 195adb47
Robert Shaw authored May 12, 2025
```
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
```
195adb47
[v1][KVCacheManager] Change prefix caching metric from counting blocks to counting tokens (#18003) · 302f3aca
Chen Zhang authored May 13, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
302f3aca
[Core] Use platform-agnostic device control for DP engine core (#17245) · 289199fe
Jade Zheng authored May 13, 2025
```
Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
```
289199fe
[Lora][Frontend]Add default local directory LoRA resolver plugin. (#16855) · 98ea3560
Jonathan Berkhahn authored May 12, 2025
```
Signed-off-by: jberkhahn <jaberkha@us.ibm.com>
```
98ea3560

[P/D] NIXL Integration (#17751) · d1911020

Robert Shaw authored May 12, 2025


Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Brent Salisbury <bsalisbu@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: ApostaC <yihua98@uchicago.edu>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Brent Salisbury <bsalisbu@redhat.com>

d1911020

Initialize the delta tool call fields explicitly (#17340) · 05a4324f
Maximilien de Bayser authored May 12, 2025
```
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: igmainc <igmainc@icloud.com>
```
05a4324f
[Misc] Improve modelscope import error (#17983) · 7ea6cb28
Jee Jee Li authored May 12, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
7ea6cb28

[Feature] Support DeepSeekV3 Function Call (#17784) · 3a5ea751

Xu Wenqing authored May 12, 2025


Signed-off-by: 许文卿 <xwq391974@alibaba-inc.com>
Signed-off-by: Xu Wenqing <xuwq1993@qq.com>

3a5ea751

[Fix] Benchmark `"EngineClient" has no attribute "model_config"` (#17976) · 891b9d33
Brayden Zhong authored May 12, 2025
```
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
```
891b9d33