Commits · fa63e710c7fbaae3a445f669d3b5ba6b9a4ef412 · OpenDAS / vllm_cscc · GitLab

26 Jan, 2025 2 commits
- [V1][Perf] Reduce scheduling overhead in model runner after cuda sync (#12094) · fa63e710
  Keyun Tong authored Jan 26, 2025
```
Signed-off-by: Keyun Tong <tongkeyun@gmail.com>
```
  fa63e710
- [Misc][Bugfix] FA3 support to ViT MHA layer (#12435) · 2a0309a6
  Roger Wang authored Jan 25, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
```
  2a0309a6
25 Jan, 2025 3 commits
- [Misc] Add FA2 support to ViT MHA layer (#12355) · f1fc0510
  Isotr0py authored Jan 25, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  f1fc0510
- [ROCm][MoE] MI300 tuned configs Mixtral-8x(7B,22B) | fp16, fp8 (#12408) · bf21481d
  Divakar Verma authored Jan 24, 2025
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
```
  bf21481d
- [Bugfix] Fix BLIP-2 processing (#12412) · fb30ee92
  Cyrus Leung authored Jan 25, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  fb30ee92
24 Jan, 2025 7 commits
- [Misc] Remove deprecated code (#12383) · df5dafaa
  Cyrus Leung authored Jan 25, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  df5dafaa
- [Bugfix][Kernel] Fix CUDA 11.8 being broken by FA3 build (#12375) · ab5bbf5a
  Lucas Wilkinson authored Jan 24, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
```
  ab5bbf5a
- [perf] fix perf regression from #12253 (#12380) · 6dd94dbe
  youkaichao authored Jan 24, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  6dd94dbe
- [V1] Increase default batch size for H100/H200 (#12369) · 0e74d797
  Woosuk Kwon authored Jan 23, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  0e74d797
- [Bugfix] Path join when building local path for S3 clone (#12353) · 5e5630a4
  omer-dayan authored Jan 24, 2025
```
Signed-off-by: Omer Dayan (SW-GPU) <omer@run.ai>
```
  5e5630a4
- Set weights_only=True when using torch.load() (#12366) · d3d6bb13
  Russell Bryant authored Jan 23, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  d3d6bb13
- [V1][Frontend] Coalesce bunched `RequestOutput`s (#12298) · 24b0205f
  Nick Hill authored Jan 23, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
```
  24b0205f
23 Jan, 2025 10 commits
- [BugFix] Fix parameter names and `process_after_weight_loading` for W4A16 MoE... · eb5cb5e5
  Dipika Sikka authored Jan 23, 2025
```
[BugFix] Fix parameter names and `process_after_weight_loading` for W4A16 MoE Group Act Order  (#11528)
Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
```
  eb5cb5e5
- [FP8][Kernel] Dynamic kv cache scaling factors computation (#11906) · e97f802b
  Gregory Shtrasberg authored Jan 23, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>
```
  e97f802b
- [torch.compile] decouple compile sizes and cudagraph sizes (#12243) · 6e650f56
  youkaichao authored Jan 24, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  6e650f56
- [core] add wake_up doc and some sanity check (#12361) · 3f50c148
  youkaichao authored Jan 24, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  3f50c148
- [Bugfix] Fix broken internvl2 inference with v1 (#12360) · 8c01b802
  Isotr0py authored Jan 24, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  8c01b802
- [V1] Simplify M-RoPE (#12352) · 99d01a5e
  Roger Wang authored Jan 23, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: imkero <kerorek@outlook.com>
```
  99d01a5e
- [Kernel] Flash Attention 3 Support (#12093) · 978b45f3
  Lucas Wilkinson authored Jan 23, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
```
  978b45f3
- [Bugfix] Fix k_proj's bias for whisper self attention (#12342) · c5b4b11d
  Isotr0py authored Jan 23, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  c5b4b11d
- [V1] Add `uncache_blocks` (#12333) · f0ef3723
  Cody Yu authored Jan 22, 2025
  
  f0ef3723
- [AMD][Quantization] Add TritonScaledMMLinearKernel since int8 is broken for AMD (#12282) · 68c4421b
  rasmith authored Jan 22, 2025
```
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
```
  68c4421b
22 Jan, 2025 14 commits
- [Frontend][V1] Online serving performance improvements (#12287) · aea94362
  Nick Hill authored Jan 22, 2025
  
  aea94362
- [Core] Support `reset_prefix_cache` (#12284) · 7206ce4c
  Cody Yu authored Jan 22, 2025
  
  7206ce4c
- [Bugfix] Fix HPU multiprocessing executor (#12167) · 96f6a759
  Konrad Zawora authored Jan 22, 2025
```
Signed-off-by: Konrad Zawora <kzawora@habana.ai>
```
  96f6a759
- [Misc] Improve the readability of BNB error messages (#12320) · 84bee4bd
  Jee Jee Li authored Jan 23, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  84bee4bd
- [Misc] Fix the error in the tip for the --lora-modules parameter (#12319) · fc66dee7
  Robin authored Jan 23, 2025
```
Signed-off-by: wangerxiao <863579016@qq.com>
```
  fc66dee7
- [Doc] Add docs for prompt replacement (#12318) · 6609cdf0
  Cyrus Leung authored Jan 22, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  6609cdf0
- [Bugfix][VLM] Fix mixed-modality inference backward compatibility for V0 (#12313) · 16366ee8
  Roger Wang authored Jan 22, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  16366ee8
- [Model][Bugfix]: correct Aria model output (#12309) · 528dbcac
  zhou fan authored Jan 22, 2025
```
Signed-off-by: xffxff <1247714429@qq.com>
```
  528dbcac
- [VLM] Avoid unnecessary tokenization (#12310) · cd7b6f08
  Cyrus Leung authored Jan 22, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  cd7b6f08
- [Core] Support fully transparent sleep mode (#11743) · 68ad4e3a
  youkaichao authored Jan 22, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  68ad4e3a
- [core] separate builder init and builder prepare for each batch (#12253) · 66818e5b
  youkaichao authored Jan 22, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  66818e5b
- [Ci/Build] Fix mypy errors on main (#12296) · cbdc4ad5
  Cyrus Leung authored Jan 22, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  cbdc4ad5
- [ci/lint] Add back default arg for pre-commit (#12279) · 64ea24d0
  Kevin H. Luu authored Jan 21, 2025
```
Signed-off-by: kevin <kevin@anyscale.com>
```
  64ea24d0
- [VLM] Simplify post-processing of replacement info (#12269) · df76e5af
  Cyrus Leung authored Jan 22, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  df76e5af
21 Jan, 2025 4 commits
- [BUGFIX] When skip_tokenize_init and multistep are set, execution crashes (#12277) · 69196a9b
  Aleksandr Malyshev authored Jan 21, 2025
```
Signed-off-by: maleksan85 <maleksan@amd.com>
Co-authored-by: maleksan85 <maleksan@amd.com>
```
  69196a9b
- [Core] Free CPU pinned memory on environment cleanup (#10477) · 9c485d9e
  Jani Monoses authored Jan 21, 2025
  
  9c485d9e
- [Misc] Set default backend to SDPA for get_vit_attn_backend (#12235) · fa9ee081
  wangxiyuan authored Jan 22, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  fa9ee081
- [Misc] Remove experimental dep from tracing.py (#12007) · 347eeebe
  Adrian Cole authored Jan 21, 2025
```
Signed-off-by: Adrian Cole <adrian.cole@elastic.co>
```
  347eeebe