Commits · 0ff70821c9b0b991197fa7f3264bf9dd78b8d4b3 · OpenDAS / vllm_cscc

"docs/vscode:/vscode.git/clone" did not exist on "38d8096760cd8f42fb65fc0ba2b9fb11f98d8ac3"

24 Nov, 2025 3 commits

[Core] Deprecate `xformers` (#29262) · 0ff70821
Roger Wang authored Nov 23, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
0ff70821

[Model] Add OpenCUA-7B support (#29068) · 30854783

Zero authored Nov 24, 2025

Signed-off-by: lim4349 <rockmanzero@naver.com>
Signed-off-by: Zero <rockmanzero@naver.com>
Co-authored-by: Cloud User <ubuntu@a100-80g-4.novalocal>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

30854783

[LoRA] Optimize 3D MoE logic (#29222) · 1073ba68
Jee Jee Li authored Nov 24, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
1073ba68

23 Nov, 2025 4 commits
- [ROCm][CI] Fix "Cannot re-initialize CUDA in forked subprocess" in test_pynccl.py (#29119) · 55c21c88
  Micah Williamson authored Nov 22, 2025
```
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
```
  55c21c88
- [CI/Build][AMD] Add check for flash_att_varlen_func to test_tree_attention.py (#29252) · 3999442f
  rasmith authored Nov 22, 2025
```
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
```
  3999442f
- [CI/Build][AMD] Skip test_multi_shared_storage_connector_consistency in... · 71362ffa
  rasmith authored Nov 22, 2025
```
[CI/Build][AMD] Skip test_multi_shared_storage_connector_consistency  in test_multi_connector.py due to hipErrorLaunchFailure  when calling .cpu() (#29253)
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
```
  71362ffa
- [Doc] Update more docs with respect to V1 (#29188) · 389aa1b2
  Cyrus Leung authored Nov 23, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  389aa1b2
22 Nov, 2025 10 commits
- [BugFix] Fix chunked prompt logprobs + preemption (#29071) · 7df331c6
  Nick Hill authored Nov 22, 2025
  
  7df331c6
- [BugFix] Fix returned logprobs with spec decode + prefill chunking (#29216) · d44a63c6
  Nick Hill authored Nov 22, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  d44a63c6
- [Attention] Refactor FA `block_size` limitations to hybrid models only (#29084) · 066209a0
  Nicolò Lucchesi authored Nov 22, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  066209a0
- [Misc] Further clean up chunked prefill and prefix caching init (#29186) · 5a480258
  Cyrus Leung authored Nov 22, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  5a480258
- [CI/Build Don't add FLASHINFER backend in test_cpu_offloading.py (#29229) · 8e22da1d
  rasmith authored Nov 22, 2025
```
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
```
  8e22da1d
- [CI/Build] Skip tests that require libcudart in test_lmcache_integration.py (#29228) · a4fdf240
  rasmith authored Nov 22, 2025
```
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
```
  a4fdf240
- [responsesAPI] parse reasoning item input (#28248) · 742e9ff6
  Andrew Xia authored Nov 21, 2025
```
Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  742e9ff6
- [CI/Build] Only use supported types and features on ROCm in MoE kernel tests (#29149) · fd65015a
  rasmith authored Nov 21, 2025
```
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
```
  fd65015a
- [CI/Build][AMD] Enable Entrypoints Integration Test (Pooling) to run without error on ROCm (#29212) · 6f403501
  rasmith authored Nov 21, 2025
```
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
```
  6f403501
- [BugFix] Fix Eagle `IndexError: list index out of range` for even `num_speculative_tokens` (#29102) · 30d64662
  Lucas Wilkinson authored Nov 21, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  30d64662
21 Nov, 2025 13 commits

[KV Connector] Fix async connector prefix cache metrics (#28585) · c6fa3895
Mark McLoughlin authored Nov 21, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
```
c6fa3895
[BugFix] EPLB + B200 + DeepGEMM : Handle column-major scales tensor (#29162) · 3137991f
Varun Sundar Rabindranath authored Nov 21, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
3137991f

Default model load/config/tokenizer to `mistral` format if relevant files exist (#28659) · 57430fc9

Julien Denize authored Nov 21, 2025


Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

57430fc9

[CI] Add batch invariant test to ci (#27842) · 1f400c58
Wentao Ye authored Nov 21, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
1f400c58

[CI/Build] Fix illegal memory access and unsupported test in... · 711241c1

rasmith authored Nov 21, 2025


[CI/Build] Fix illegal memory access and unsupported test in kernels/attention/test_cache.py (#29118)
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>

711241c1

[V0 deprecation] Remove more V0 references (#29088) · aab0102a
Cyrus Leung authored Nov 21, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
aab0102a
[Misc] remove useless v1 env (#29164) · b34129bf
WeiQing Chen authored Nov 21, 2025
```
Signed-off-by: David Chen <530634352@qq.com>
```
b34129bf
[Bugfix] Fix default MM LoRA alignment for single str prompts (#29140) · b4734b95
Alex Brooks authored Nov 20, 2025
```
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
```
b4734b95
Revert "[Redo] #26368 (#28771)" (#29121) · 30b9c677
Jialin Ouyang authored Nov 20, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
30b9c677
[V0 Deprecation] Remove `best_of` (#29090) · 56e96b37
Cyrus Leung authored Nov 21, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
56e96b37
[Core] Add audio_embeds support to chat completions (#29059) · 07304149
jeremyteboul authored Nov 20, 2025
```
Signed-off-by: Jeremy Teboul <jeremyteboul@fb.com>
Co-authored-by: Jeremy Teboul <jeremyteboul@fb.com>
```
07304149
[LoRA][2/2]Remove LoRA extra vocab (#28545) · 9875be64
Jee Jee Li authored Nov 21, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
9875be64

Update model references for OLMo3 (#29099) · 87cbbdff

Michael Goin authored Nov 20, 2025


Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

87cbbdff

20 Nov, 2025 10 commits
- [CI/Build] Remove skip global cleanup in test_struct_output_generate.py (#29022) · c7a29d2c
  rasmith authored Nov 20, 2025
```
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
```
  c7a29d2c
- [CI/Build] Skip lm-format-enforcer tests in test_struct_output_generate.py for now (#29021) · 8237ab8a
  rasmith authored Nov 20, 2025
```
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
```
  8237ab8a
- [CI/Build] Make test_attention_selector.py run tests on correct platform (#29064) · 5e5a7eb1
  rasmith authored Nov 20, 2025
```
Signed-off-by: Randall Smith <ransmith@amd.com>
Signed-off-by: rasmith <Randall.Smith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  5e5a7eb1
- [CI/Build][AMD] Skip if flash_attn_varlen_func not available in test_aiter_flash_attn.py (#29043) · 3d84ef90
  rasmith authored Nov 20, 2025
```
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
```
  3d84ef90
- [KVConnector][Core] Support cross-layer KV blocks (#27743) · 64746471
  Or Ozeri authored Nov 20, 2025
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  64746471
- [BugFix] [FEAT] Enable fastsafetensors for ROCm platform (#28225) · 82b05b15
  TJian authored Nov 20, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  82b05b15
- [MODEL] Implement plamo3 (#28834) · c9e09311
  Shinichi Hemmi authored Nov 20, 2025
```
Signed-off-by: Shinichi Hemmi <50256998+Alnusjaponica@users.noreply.github.com>
```
  c9e09311
- [BugFix] kv_offloading: Fix bug in loading of partial cpu blocks (#28951) · c0c2dd1e
  Or Ozeri authored Nov 20, 2025
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  c0c2dd1e
- [Bugfix][cache_kernels]: Fix OOB in cache_kernels.cu (#28760) · fb8851f2
  Vensen authored Nov 20, 2025
```
Signed-off-by: vensen <vensenmu@gmail.com>
Signed-off-by: Vensenmu <vensenmu@gmail.com>
```
  fb8851f2
- [CI/Build][AMD] Fix import errors in tests/kernels/attention (#29032) · 322cb028
  rasmith authored Nov 20, 2025
```
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
```
  322cb028