Commits · 3f1fc7425a7db4d9722941075e43bb2ebfb90613 · OpenDAS / vllm_cscc

27 Jan, 2025 8 commits
- [V1][Metrics] Add initial Prometheus logger (#12416) · 01ba9270
  Mark McLoughlin authored Jan 27, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  01ba9270
- [Bugfix] Fix gpt2 GGUF inference (#12467) · ce69f7f7
  Isotr0py authored Jan 27, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  ce69f7f7
- [V1][Minor] Minor optimizations for update_from_output (#12454) · 624a1e47
  Woosuk Kwon authored Jan 27, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  624a1e47
- [Bugfix] Fix missing seq_start_loc in xformers prefill metadata (#12464) · 372bf089
  Isotr0py authored Jan 27, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  372bf089
- [Bugfix] Fix Granite 3.0 MoE model loading (#12446) · 5204ff5c
  Cyrus Leung authored Jan 27, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  5204ff5c
- [Frontend] Support scores endpoint in run_batch (#12430) · 0cc6b383
  Pooya Davoodi authored Jan 26, 2025
```
Signed-off-by: Pooya Davoodi <pooya.davoodi@parasail.io>
```
  0cc6b383
- [V1] Avoid list creation in input preparation (#12457) · 28e07508
  Woosuk Kwon authored Jan 26, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  28e07508
- [Frontend] Rerank API (Jina- and Cohere-compatible API) (#12376) · 0034b09c
  Kyle Mistele authored Jan 26, 2025
```
Signed-off-by: Kyle Mistele <kyle@mistele.com>
```
  0034b09c
26 Jan, 2025 7 commits

[Bugfix/CI] Fix broken kernels/test_mha.py (#12450) · 72f48804
Tyler Michael Smith authored Jan 26, 2025

72f48804
[Bugfix] Disable w16a16 2of4 sparse CompressedTensors24 (#12417) · aa2cd2c4
Tyler Michael Smith authored Jan 26, 2025
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
```
aa2cd2c4

[Frontend] generation_config.json for maximum tokens(#12242) · 9ddc3522

Matthew Hendrey authored Jan 26, 2025


Signed-off-by: Matthew Hendrey <matthew.hendrey@gmail.com>
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: shangmingc <caishangming@linux.alibaba.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Yuan Tang <terrytangyuan@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>

9ddc3522

[Misc] Revert FA on ViT #12355 and #12435 (#12445) · a5255270
Roger Wang authored Jan 26, 2025

a5255270
[V1][Bugfix] Fix assertion when mm hashing is turned off (#12439) · 0ee349b5
Roger Wang authored Jan 26, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
0ee349b5
[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 5 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