Commits · fefce49807a52fc94678e336fc5d1f3b7ebe2daf · OpenDAS / vllm_cscc · GitLab

13 Jan, 2026 7 commits
- [Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240) · fefce498
  Chauncey authored Jan 13, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  fefce498
- [Bugfix] Replace `PoolingParams.normalize` with `use_activation` (#32243) · 232214b2
  Cyrus Leung authored Jan 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  232214b2
- [ROCm][CI] Fix engine core client tests for ROCm spawn multiprocessing (#32061) · df7e1271
  Andreas Karatzas authored Jan 13, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  df7e1271
- [BugFix]Fix eagle draft_model_config and add tests (#31753) · 80221e18
  Xingyu Liu authored Jan 12, 2026
```
Signed-off-by: Xingyu Liu <charlotteliu12x@gmail.com>
```
  80221e18
- [ROCm][CI] Fix HuggingFace flash_attention_2 accuracy issue in Isaac vision encoder (#32233) · 5e714f7f
  Andreas Karatzas authored Jan 13, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  5e714f7f
- [BugFix] Fix engine crash caused by chat tools + response_format (#32127) · c6bb5b56
  Nick Hill authored Jan 12, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  c6bb5b56
- [responsesAPI] add unit test for optional function tool call id (#32036) · a307ac07
  Andrew Xia authored Jan 12, 2026
```
Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>
```
  a307ac07
12 Jan, 2026 12 commits
- [NIXL][Bugfix] Failure logging overhaul + early metadata free on failure (#32031) · f8bd8394
  Nicolò Lucchesi authored Jan 12, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  f8bd8394
- [BugFix] scheduler: Fix ordering preserving of skipped requests (#32173) · 2be765b6
  Or Ozeri authored Jan 12, 2026
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  2be765b6
- [Refactor] EPLB rebalance algo to NumPy (#30697) · 1eb61ab3
  Ilya Markov authored Jan 12, 2026
```
Signed-off-by: ilmarkov <markovilya197@gmail.com>
```
  1eb61ab3
- [3/N][Attention] Move AttentionMetadata-related code from utils.py to backend.py (#32054) · 20228cb8
  Matthew Bonanni authored Jan 12, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  20228cb8
- [Benchmark] Share data between SLA runs (#32184) · 7c0d3c51
  Cyrus Leung authored Jan 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  7c0d3c51
- [Misc][PD] Fix `get_attn_backend` usage in transfer connectors (#31988) · 5b681074
  Nicolò Lucchesi authored Jan 12, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  5b681074
- [Bugfix] Fix stale SSM state for new Mamba requests scheduled as decode (#32118) · 8fb2c135
  Asaf Joseph Gardin authored Jan 12, 2026
```
Signed-off-by: Josephasafg <ajgard7@gmail.com>
```
  8fb2c135
- [FIX] Add NO_MUL activation support for modular kernel path (#31528) · 3f72639d
  danielafrimi authored Jan 12, 2026
```
Signed-off-by: dafrimi <dafrimi@nvidia.com>
Signed-off-by: <>
Co-authored-by: root <root@gpu-267.slurm-workers-slurm.slurm.svc.cluster.local>
Co-authored-by: root <root@gpu-537.slurm-workers-slurm.slurm.svc.cluster.local>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: root <root@pool0-01777.cm.cluster>
```
  3f72639d
- [MODEL] New model support for kakaocorp/kanana-1.5-v-3b-instruct (#29384) · 6bc9c847
  Jaehyun An authored Jan 13, 2026
```
Signed-off-by: Jaehyun An <steve.ai@kakaocorp.com>
```
  6bc9c847
- Add K-EXAONE-236B-A23B (#31621) · 63ed2409
  Kyungmin Lee authored Jan 13, 2026
```
Signed-off-by: lkm2835 <lkm2835@gmail.com>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: lgai-exaone <exaonemodels@lgresearch.ai>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  63ed2409
- OffloadingConnector: Add cpu_bytes_to_use configuration (#24498) · 9cddbdba
  Or Ozeri authored Jan 12, 2026
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  9cddbdba
- [Frontend] Fix Flaky MCP Streaming Test (#32153) · d7b2e570
  daniel-salib authored Jan 12, 2026
```
Signed-off-by: Daniel Salib <danielsalib@meta.com>
```
  d7b2e570
11 Jan, 2026 5 commits
- [CI] fix `test_concat_and_cache_mla_rope_fused` (#32117) · 3df619ac
  Jiangyun Zhu authored Jan 11, 2026
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  3df619ac
- [CI/Build] Separate out flaky responses API tests (#32110) · a3745321
  Cyrus Leung authored Jan 11, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  a3745321
- [KVConnector] OffloadingConnector: Fix bug in handling of preemptions (#29870) · 4c16ba61
  Or Ozeri authored Jan 11, 2026
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  4c16ba61
- [Hardware][AMD][CI][Bugfix] Fix AMD Quantization test group (#31713) · bde57ab2
  Matt authored Jan 11, 2026
```
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
```
  bde57ab2
- [Benchmark][2/2] Use spline interpolation to tune SLA variables (#32095) · ef96fa3f
  Cyrus Leung authored Jan 11, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ef96fa3f
10 Jan, 2026 11 commits
- [BugFix] Wait for compute before offloading KV to CPU (#31341) · 2a4dbe24
  Or Ozeri authored Jan 11, 2026
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  2a4dbe24
- Revert "[Kernels][FI] Skip trtllm attention when num_kv_heads=1 (#308… (#31617) · 1c46dea0
  shyeh25 authored Jan 11, 2026
```
Signed-off-by: shyeh25 <206795756+shyeh25@users.noreply.github.com>
```
  1c46dea0
- [BugFix] scheduler: Fix resuming of preempted requests after async load (#31583) · 02859973
  Or Ozeri authored Jan 10, 2026
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  02859973
- [Bugfix] Fix integer overflow in Gemma3n audio processing (#31657) · 07286ec5
  Jeremy Teboul authored Jan 10, 2026
```
Signed-off-by: Jeremy Teboul <jeremyte@meta.com>
```
  07286ec5
- [Benchmark][1/2] Generalize SLA criterion validation from binary flags to margins (#32075) · 5f2385a4
  Cyrus Leung authored Jan 10, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  5f2385a4
- [ROCm][CI] Fix flaky `test_function_calling_with_stream` and reduce schema test examples (#32063) · d83becd5
  Andreas Karatzas authored Jan 09, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  d83becd5
- [Refactor] Separate sequence and token pooling types (#32026) · 583a90e0
  Cyrus Leung authored Jan 10, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  583a90e0
- Fuse RoPE and MLA KV-cache write (#25774) · 80fead8b
  PatrykSaffer authored Jan 10, 2026
```
Signed-off-by: Patryk Saffer <patryk.saffer99@gmail.com>
Signed-off-by: PatrykSaffer <patryk.saffer@mistral.ai>
Co-authored-by: Patryk Saffer <patryk.saffer99@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  80fead8b
- feature/issac 0.2 (#31550) · e45946bd
  Akshat Shrivastava authored Jan 09, 2026
```
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  e45946bd
- [Misc][LLaMa4] Compile LLaMa Vision Encoder (#30709) · ea6d067a
  Lucas Kabela authored Jan 09, 2026
```
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
```
  ea6d067a
- resolve pydantic error in startup benchmark (#31348) · abd92242
  Ning Xie authored Jan 10, 2026
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  abd92242
09 Jan, 2026 5 commits
- [1/N][Attention] Restructure attention: move files (#31916) · 2612ba92
  Matthew Bonanni authored Jan 09, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  2612ba92
- [responsesAPI] fix incomplete_messages for simple/parsable context (#31836) · 1f8b7c53
  Andrew Xia authored Jan 09, 2026
```
Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>
```
  1f8b7c53
- [Quant] Make static quant support all group shapes (#30833) · 0a0aa077
  Lucas Wilkinson authored Jan 09, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  0a0aa077
- Add unpermute-aware fused MoE path and small-batch fallback (#29354) · a4d5d663
  Runkai Tao authored Jan 09, 2026
```
Signed-off-by: Runkai Tao <rt572@physics.rutgers.edu>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  a4d5d663
- [Fix] Introduce audio channels spec (#31595) · 657e9c0e
  Jeremy Teboul authored Jan 09, 2026
```
Signed-off-by: Jeremy Teboul <jeremyte@meta.com>
```
  657e9c0e