Commits · 71470bc4afdab89eccc232b668a69571ffede1dc · OpenDAS / vllm_cscc

31 Jul, 2025 4 commits
- [Misc] Add unit tests for chunked local attention (#21692) · 71470bc4
  Yong Hoon Shin authored Jul 31, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  71470bc4
- [Meta] Official Eagle mm support, first enablement on llama4 (#20788) · 9e0726e5
  zhiweiz authored Jul 31, 2025
```
Signed-off-by: morgendave <morgendave@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.me>
```
  9e0726e5
- [BugFix] Fix case where `collective_rpc` returns `None` (#22006) · 5daffe7c
  Nick Hill authored Jul 31, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  5daffe7c
- [CI Bugfix] Fix CI OOM for `test_shared_storage_connector_hashes` (#21973) · 055bd397
  Michael Goin authored Jul 30, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  055bd397
30 Jul, 2025 7 commits
- [Core] Move EngineCoreRequest to Request conversion out of EngineCore (#21627) · ca9e2be3
  Zebing Lin authored Jul 30, 2025
```
Signed-off-by: linzebing <linzebing1995@gmail.com>
```
  ca9e2be3
- [Misc] Support more collective_rpc return types (#21845) · 56bd537d
  Nick Hill authored Jul 30, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  56bd537d
- [Bugfix] SharedStorage Connector for V1 PD multimodal (#21611) · 4904e53c
  Chenguang Zheng authored Jul 31, 2025
```
Signed-off-by: fake0fan <645327136@qq.com>
Signed-off-by: herotai214 <herotai214@gmail.com>
Co-authored-by: herotai214 <herotai214@gmail.com>
```
  4904e53c
- [Bugfix] Fix TypeError in scheduler when comparing mixed request_id types (#21816) · 5c765aec
  633WHU authored Jul 30, 2025
```
Signed-off-by: chiliu <chiliu@paypal.com>
Co-authored-by: chiliu <chiliu@paypal.com>
```
  5c765aec
- Override attention metadata for fast prefill in some KV sharing setups (#21590) · ad510309
  Yong Hoon Shin authored Jul 30, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  ad510309
- [Misc] Improve code readability of KVCacheManager (#21673) · 8f4a1c9a
  Ruixiang Tan authored Jul 30, 2025
```
Signed-off-by: tanruixiang <tanruixiang0104@gmail.com>
Signed-off-by: Ruixiang Tan <819464715@qq.com>
Signed-off-by: GitHub <noreply@github.com>
```
  8f4a1c9a
- [v1][attention] Support Hybrid Allocator + FlashInfer (#21412) · 555e7225
  Chen Zhang authored Jul 29, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  555e7225
29 Jul, 2025 2 commits

[KVCache] Make KVCacheSpec hashable (#21791) · 755fa8b6
Chen Zhang authored Jul 29, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
755fa8b6

[V0 deprecation] Guided decoding (#21347) · 37efc63b

Reza Barazesh authored Jul 29, 2025

Signed-off-by: Reza Barazesh <rezabarazesh@meta.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

37efc63b

28 Jul, 2025 4 commits
- Revert "[V1] Exception Handling when Loading KV Cache from Remote Store" (#21778) · b18b417f
  Kuntai Du authored Jul 28, 2025
```
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
```
  b18b417f
- [v1][mamba] Added mamba_type into MambaSpec (#21715) · a6c05028
  Asaf Joseph Gardin authored Jul 28, 2025
```
Signed-off-by: asafg <asafg@ai21.com>
Co-authored-by: asafg <asafg@ai21.com>
```
  a6c05028
- [V1] Exception Handling when Loading KV Cache from Remote Store (#21534) · 15a72ac4
  Adeline authored Jul 28, 2025
```
Signed-off-by: liuyumoye <adeline_ly2023@outlook.com>
Co-authored-by: liuyumoye <adeline_ly2023@outlook.com>
```
  15a72ac4
- [Deprecation][2/N] Replace `--task` with `--runner` and `--convert` (#21470) · 86ae693f
  Cyrus Leung authored Jul 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  86ae693f
26 Jul, 2025 1 commit

Support encoder-only models without KV-Cache (#21270) · 1cd6eaba

Maximilien de Bayser authored Jul 26, 2025


Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>

1cd6eaba

25 Jul, 2025 5 commits
- [TPU][Test] Rollback PR-21550. (#21619) · 7cfea0df
  QiliangCui authored Jul 25, 2025
```
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
```
  7cfea0df
- [Tests] Harden DP tests (#21508) · e38e96a3
  Nick Hill authored Jul 25, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  e38e96a3
- [TPU][Bugfix] fix OOM issue in CI test (#21550) · 40d86ee4
  Chengji Yao authored Jul 24, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
```
  40d86ee4
- [TPU][Test] Temporarily suspend this MoE model in test_basic.py. (#21560) · e0be2c4d
  QiliangCui authored Jul 24, 2025
```
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
```
  e0be2c4d
- [DP] Support api-server-count > 0 in hybrid DP LB mode (#21510) · 9c8b2c2a
  Nick Hill authored Jul 25, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  9c8b2c2a
24 Jul, 2025 6 commits

[P/D] Support CPU Transfer in NixlConnector (#18293) · 60662849

Juncheng Gu authored Jul 24, 2025


Signed-off-by: Juncheng Gu <juncgu@gmail.com>
Signed-off-by: Richard Liu <ricliu@google.com>
Co-authored-by: Richard Liu <39319471+richardsliu@users.noreply.github.com>
Co-authored-by: Richard Liu <ricliu@google.com>

60662849

[P/D] Move FakeNixlWrapper to test dir (#21328) · 1e9ea8e6
Rui Qiao authored Jul 24, 2025
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
1e9ea8e6
[Attention] Optimize FlashInfer MetadataBuilder Build call (#21137) · 61b8cea3
Lucas Wilkinson authored Jul 24, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
61b8cea3
[v1][Core] Clean up usages of `SpecializedManager` (#21407) · fc5f756d
Zhou Fang authored Jul 24, 2025
```
Signed-off-by: Zhou Fang <fang.github@gmail.com>
```
fc5f756d

[TPU][Bugfix] fix moe layer (#21340) · e74bfc70

Chengji Yao authored Jul 24, 2025


Signed-off-by: Chengji Yao <chengjiyao@google.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>

e74bfc70

[DP] Internal Load Balancing Per Node [`one-pod-per-node`] (#21238) · d5b981f8

Robert Shaw authored Jul 23, 2025


Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

d5b981f8

23 Jul, 2025 4 commits
- [Core] Add `reload_weights` RPC method (#20096) · 5c9b807b
  22quinn authored Jul 23, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  5c9b807b
- [Tests] Add tests for headless internal DP LB (#21450) · 316b1bf7
  Nick Hill authored Jul 23, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  316b1bf7
- [Sampler] Introduce logprobs mode for logging (#21398) · accac829
  Lu Fang authored Jul 23, 2025
```
Signed-off-by: Lu Fang <lufang@fb.com>
```
  accac829
- [Core] Add basic unit test for maybe_evict_cached_block (#21400) · a1f3610f
  Jialin Ouyang authored Jul 23, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  a1f3610f
22 Jul, 2025 2 commits
- [Core] Introduce popleft_n and append_n in FreeKVCacheBlockQueue to further... · ed250545
  Jialin Ouyang authored Jul 22, 2025
```
[Core] Introduce popleft_n and append_n in FreeKVCacheBlockQueue to further optimize block_pool (#21222)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  ed250545
- [V1] [Hybrid] Add new test to verify that hybrid views into KVCacheTensor are compatible (#21300) · 488d8a98
  Thomas Parnell authored Jul 22, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  488d8a98
21 Jul, 2025 2 commits
- [DP] Fix Prometheus Logging (#21257) · 29d1ffc5
  Robert Shaw authored Jul 21, 2025
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  29d1ffc5
- [Misc] unify variable for LLM instance (#20996) · d9784107
  Ning Xie authored Jul 21, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  d9784107
20 Jul, 2025 3 commits
- [bugfix] fix syntax warning caused by backslash (#21251) · 7ba34b12
  Jiayi Yan authored Jul 21, 2025
  
  7ba34b12
- Enable v1 metrics tests (#20953) · d1fb65bd
  Seiji Eicher authored Jul 19, 2025
```
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
```
  d1fb65bd
- [TPU] support fp8 kv cache quantization (#19292) · 3a1d8940
  Chengji Yao authored Jul 19, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
```
  3a1d8940