Commits · 322d2a27d66eb1896272e76640e5dfdec6fb4fcc · OpenDAS / vllm_cscc

"vscode:/vscode.git/clone" did not exist on "52dceb172d6fe762bb60b670df61866fe86b6f17"

23 Feb, 2025 1 commit
- [BugFix] Minor: logger import in attention backend (#13706) · 322d2a27
  Andy Lo authored Feb 23, 2025
```
Signed-off-by: Andy Lo <andy@mistral.ai>
```
  322d2a27
22 Feb, 2025 19 commits
- [Bugfix] Fix boolean conversion for OpenVINO env variable (#13615) · 382f66fb
  Helena Kloosterman authored Feb 22, 2025
  
  382f66fb
- [ROCm] Apply FP8 weights padding to values not divisible by 512 bytes on ROCm (#13231) · c904fddd
  Gregory Shtrasberg authored Feb 22, 2025
  
  c904fddd
- [V1][Kernel] Refactor the prefix_prefill kernel so that the caller no longer... · 558db808
  Sage Moore authored Feb 22, 2025
```
[V1][Kernel] Refactor the prefix_prefill kernel so that the caller no longer has to pass in the context lengths (#13095)
```
  558db808
- [NVIDIA] Support nvfp4 cutlass gemm (#13571) · e109e598
  Kaixi Hou authored Feb 22, 2025
  
  e109e598
- Support SSL Key Rotation in HTTP Server (#13495) · 8db1b9d0
  Keyun Tong authored Feb 22, 2025
  
  8db1b9d0
- [ci] fix linter (#13701) · 2382ad29
  youkaichao authored Feb 22, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  2382ad29
- [core] set up data parallel communication (#13591) · 3e472d88
  youkaichao authored Feb 22, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  3e472d88
- [CI/Build] Fix pre-commit errors (#13696) · 7f6bae56
  Cyrus Leung authored Feb 22, 2025
  
  7f6bae56
- [Misc] Reduce LoRA-related static variable (#13166) · 105b8ce4
  Jee Jee Li authored Feb 22, 2025
  
  105b8ce4
- [Metrics] Add `--show-hidden-metrics-for-version` CLI arg (#13295) · 2cb8c154
  Mark McLoughlin authored Feb 22, 2025
  
  2cb8c154
- [V1][Metrics] Support `vllm:cache_config_info` (#13299) · 1cd981da
  Mark McLoughlin authored Feb 22, 2025
  
  1cd981da
- Correction to TP logic for Mamba Mixer 2 when Num Groups not divisible by TP Size (#13660) · fca20841
  Yu Chin Fabian Lim authored Feb 22, 2025
  
  fca20841
- [Bugfix] V1 Memory Profiling: V0 Sampler Integration without Rejection Sampler (#13594) · da31b533
  Jennifer Zhao authored Feb 22, 2025
```
Signed-off-by: Jennifer Zhao <7443418+JenZhao@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
```
  da31b533
- [v1] Support allowed_token_ids in v1 Sampler (#13210) · bb78fb31
  Lu Fang authored Feb 21, 2025
```
Signed-off-by: Lu Fang <lufang@fb.com>
```
  bb78fb31
- [Bugfix][Model] OLMo 2: split qkv correctly for GQA and MQA (#13687) · 9a1f1da5
  Shane A authored Feb 21, 2025
  
  9a1f1da5
- [ROCM] fix native attention function call (#13650) · 68d630a0
  Gordon Wong authored Feb 22, 2025
  
  68d630a0
- [Misc] Capture and log the time of loading weights (#13666) · 68d535ef
  Jun Duan authored Feb 22, 2025
  
  68d535ef
- [Bugfix][API Server] Fix invalid usage of 'ge' and 'le' in port valid… (#13672) · c6ed9386
  Robin authored Feb 22, 2025
  
  c6ed9386
- [HTTP Server] Make model param optional in request (#13568) · 0ffdf8ce
  Keyun Tong authored Feb 21, 2025
  
  0ffdf8ce
21 Feb, 2025 7 commits
- [Attention] MLA with chunked prefill (#12639) · 288cc6c2
  Lucas Wilkinson authored Feb 21, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Patrick Horn <patrick.horn@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  288cc6c2
- [Bugfix][CPU] Fix cpu all-reduce using native pytorch implementation (#13586) · b2c3fc5d
  Isotr0py authored Feb 21, 2025
  
  b2c3fc5d
- [FEATURE] Enables /score endpoint for embedding models (#12846) · 1c3c9757
  Gabriel Marinho authored Feb 21, 2025
  
  1c3c9757
- [V1][Sampler] Avoid an operation during temperature application (#13587) · 31aa045c
  Nick Hill authored Feb 20, 2025
  
  31aa045c
- [Bugfix] Add `mm_processor_kwargs` to chat-related protocols (#13644) · a30c0935
  Roger Wang authored Feb 20, 2025
  
  a30c0935
- [Neuron][Kernel] Vectorize KV cache load in FlashPagedAttention to maximize DMA bandwidth (#13245) · 33170081
  Lingfan Yu authored Feb 20, 2025
```
Signed-off-by: Lingfan Yu <lingfany@amazon.com>
```
  33170081
- [Bugfix] Fix max_num_batched_tokens for MLA (#13620) · 71face85
  Michael Goin authored Feb 20, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  71face85
20 Feb, 2025 13 commits
- [Frontend] Add backend-specific options for guided decoding (#13505) · bfbc0b32
  Joe Runde authored Feb 20, 2025
```
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
```
  bfbc0b32
- fix neuron performance issue (#13589) · 6a417b86
  ajayvohra2005 authored Feb 20, 2025
  
  6a417b86
- [V1][Minor] Print KV cache size in token counts (#13596) · d3ea5011
  Woosuk Kwon authored Feb 20, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  d3ea5011
- [Bugfix] Fix deepseekv3 grouped topk error (#13474) · ed6e9075
  chenxiaobing authored Feb 20, 2025
```
Signed-off-by: Chen-XiaoBing <chenxb002@whu.edu.cn>
```
  ed6e9075
- [Kernel] LoRA - Refactor sgmv kernels (#13110) · b69692a2
  Varun Sundar Rabindranath authored Feb 20, 2025
  
  b69692a2
- [API Server] Add port number range validation (#13506) · 3738e6fa
  Yuan Tang authored Feb 20, 2025
```
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
```
  3738e6fa
- [ROCm] MI300A compile targets deprecation (#13560) · 0023cd2b
  Gregory Shtrasberg authored Feb 20, 2025
  
  0023cd2b
- [Misc] add mm_processor_kwargs to extra_body for Qwen2.5-VL (#13533) · 041e2947
  燃 authored Feb 20, 2025
  
  041e2947
- [Misc] Warn if the vLLM version can't be retrieved (#13501) · 96216678
  Alex Brooks authored Feb 19, 2025
```
Signed-off-by: Alex-Brooks <Alex.brooks@ibm.com>
```
  96216678
- [bugfix] spec decode worker get tp group only when initialized (#13578) · 8c755c3b
  Simon Mo authored Feb 19, 2025
  
  8c755c3b
- [core] add sleep and wake up endpoint and v1 support (#12987) · ba811639
  youkaichao authored Feb 20, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: cennn <2523403608@qq.com>
Co-authored-by: cennn <2523403608@qq.com>
```
  ba811639
- [ROCm][MoE] mi300 mixtral8x7B perf for specific BS (#13577) · 0d243f2a
  Divakar Verma authored Feb 19, 2025
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
```
  0d243f2a
- [Misc] Qwen2.5 VL support LoRA (#13261) · 512368e3
  Jee Jee Li authored Feb 20, 2025
  
  512368e3