Commits · 83609791d2ceeb628e0d1f5ea60a64c132eb083c · OpenDAS / vllm_cscc · GitLab

20 Jan, 2025 6 commits
- [Model] Add Qwen2 PRM model support (#12202) · 83609791
  Isotr0py authored Jan 20, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  83609791
- [Bugfix] Fix incorrect types in LayerwiseProfileResults (#12196) · 0974c9bc
  Yuan Tang authored Jan 20, 2025
```
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
```
  0974c9bc
- [DOC] Add missing docstring in LLMEngine.add_request() (#12195) · d2643128
  Yuan Tang authored Jan 20, 2025
```
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
```
  d2643128
- [DOC] Fix typo in docstring and assert message (#12194) · c5c06209
  Yuan Tang authored Jan 20, 2025
```
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
```
  c5c06209
- [torch.compile] fix sym_tensor_indices (#12191) · 51ef828f
  youkaichao authored Jan 20, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  51ef828f
- [Bugfix] Fix num_heads value for simple connector when tp enabled (#12074) · df450aa5
  shangmingc authored Jan 20, 2025
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  df450aa5
19 Jan, 2025 8 commits
- [Model] Support for fairseq2 Llama (#11442) · bbe5f9de
  Martin Gleize authored Jan 19, 2025
```
Signed-off-by: Martin Gleize <mgleize@meta.com>
Co-authored-by: mgleize user <mgleize@a100-st-p4de24xlarge-4.fair-a100.hpcaas>
```
  bbe5f9de
- [V1] Add V1 support of Qwen2-VL (#12128) · 81763c58
  Roger Wang authored Jan 19, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: imkero <kerorek@outlook.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  81763c58
- [Misc] Add BNB support to GLM4-V model (#12184) · edaae198
  Isotr0py authored Jan 19, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  edaae198
- [torch.compile] store inductor compiled Python file (#12182) · e66faf48
  youkaichao authored Jan 19, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  e66faf48
- [Bugfix] Fix multi-modal processors for transformers 4.48 (#12187) · 630eb5b5
  Cyrus Leung authored Jan 19, 2025
  
  630eb5b5
- [BUGFIX] Move scores to float32 in case of running xgrammar on cpu (#12152) · 4e94951b
  Michal Adamczyk authored Jan 19, 2025
```
Signed-off-by: Michal Adamczyk <madamczyk@habana.ai>
```
  4e94951b
- [V1] Collect env var for usage stats (#12115) · 7a8a48d5
  Simon Mo authored Jan 18, 2025
  
  7a8a48d5
- [Misc] Support register quantization method out-of-tree (#11969) · 32eb0da8
  yancong authored Jan 19, 2025
  
  32eb0da8
18 Jan, 2025 4 commits
- [core] clean up executor class hierarchy between v1 and v0 (#12171) · 6d0e3d37
  youkaichao authored Jan 18, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  6d0e3d37
- [Model] Port deepseek-vl2 processor, remove dependency (#12169) · 02798eca
  Isotr0py authored Jan 18, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  02798eca
- [core] further polish memory profiling (#12126) · da02cb4b
  youkaichao authored Jan 18, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  da02cb4b
- [misc] fix cross-node TP (#12166) · 2b835032
  youkaichao authored Jan 18, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  2b835032
17 Jan, 2025 9 commits
- [torch.compile] disable logging when cache is disabled (#12043) · 7b98a65a
  youkaichao authored Jan 18, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  7b98a65a
- [AMD][FP8] Using MI300 FP8 format on ROCm for block_quant (#12134) · b5b57e30
  Gregory Shtrasberg authored Jan 17, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  b5b57e30
- [Bugfix] Mistral tokenizer encode accept list of str (#12149) · 54cacf00
  Kunshang Ji authored Jan 18, 2025
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  54cacf00
- [Bugfix] Fix score api for missing max_model_len validation (#12119) · 58fd57ff
  Wallas Henrique authored Jan 17, 2025
```
Signed-off-by: Wallas Santos <wallashss@ibm.com>
```
  58fd57ff
- [core] allow callable in collective_rpc (#12151) · 87a0c076
  youkaichao authored Jan 17, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  87a0c076
- [CI/Build][CPU][Bugfix] Fix CPU CI (#12150) · d4e61945
  Li, Jiang authored Jan 17, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  d4e61945
- [Misc][LoRA] Improve the readability of LoRA error messages (#12102) · 07934cc2
  Jee Jee Li authored Jan 17, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  07934cc2
- [V1] Move more control of kv cache initialization from model_executor to EngineCore (#11960) · 69d765f5
  Chen Zhang authored Jan 17, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
```
  69d765f5
- [BugFix] add more `is not None` check in VllmConfig.__post_init__ (#12138) · d1adb9b4
  Chen Zhang authored Jan 17, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  d1adb9b4
16 Jan, 2025 8 commits
- [Bugfix] Set enforce_eager automatically for mllama (#12127) · d06e8240
  Chen Zhang authored Jan 17, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  d06e8240
- [Model] Add support for deepseek-vl2-tiny model (#12068) · 62b06ba2
  Isotr0py authored Jan 17, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  62b06ba2
- [Bugfix] Fix max image feature size for Llava-one-vision (#12104) · 874f7c29
  Roger Wang authored Jan 16, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  874f7c29
- [core] LLM.collective_rpc interface and RLHF example (#12084) · 92e793d9
  youkaichao authored Jan 16, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  92e793d9
- Support torchrun and SPMD-style offline inference (#12071) · bf53e0c7
  youkaichao authored Jan 16, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  bf53e0c7
- [Bugfix] Remove hardcoded `head_size=256` for Deepseek v2 and v3 (#12067) · dd7c9ad8
  Isotr0py authored Jan 16, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  dd7c9ad8
- Various cosmetic/comment fixes (#12089) · 9aa1519f
  Michael Goin authored Jan 16, 2025
```
Signed-off-by: mgoin <michael@neuralmagic.com>
```
  9aa1519f
- [Core] Default to using per_token quantization for fp8 when cutlass is supported. (#8651) · fa0050db
  Elfie Guo authored Jan 15, 2025
```
Signed-off-by: mgoin <michael@neuralmagic.com>
Co-authored-by: Michael Goin <mgoin@redhat.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
```
  fa0050db
15 Jan, 2025 5 commits
- [Bugfix] Fix _get_lora_device for HQQ marlin (#12090) · ebd8c669
  Varun Sundar Rabindranath authored Jan 16, 2025
```
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
```
  ebd8c669
- [V1][Core] Autotune encoder cache budget (#11895) · 70755e81
  Roger Wang authored Jan 15, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  70755e81
- [Bugfix] use right truncation for non-generative tasks (#12050) · edce722e
  Joe Runde authored Jan 15, 2025
```
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
```
  edce722e
- [Doc]: Update `OpenAI-Compatible Server` documents (#12082) · 57e729e8
  maang-h authored Jan 16, 2025
  
  57e729e8
- [Misc][Quark] Upstream Quark format to VLLM (#10765) · de0526f6
  kewang-xlnx authored Jan 16, 2025
```
Signed-off-by: kewang-xlnx <kewang@xilinx.com>
Signed-off-by: kewang2 <kewang2@amd.com>
Co-authored-by: kewang2 <kewang2@amd.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
```
  de0526f6