Commits · 09e372e796a82da8bb24f1fcde60f804c023cf68 · OpenDAS / vllm_cscc

13 May, 2025 1 commit
- add qwen3 moe configs · 09e372e7
  zhuwenwen authored May 13, 2025
```
support telechat2 and glm4 nn layout
remove log of request_id
```
  09e372e7
09 May, 2025 6 commits
- roll back unused change · 29e922ac
  lizhigong authored May 09, 2025
  
  29e922ac
- rm debug log · 7d224eb2
  lizhigong authored May 08, 2025
  
  7d224eb2
- debug spec decode zero overhead · 0ecda6d1
  lizhigong authored May 08, 2025
  
  0ecda6d1
- add spec decode zero overhead · 01c30741
  lizhigong authored Apr 27, 2025
  
  01c30741
- debug v0 zero overhead schedule · 4ff58b66
  lizhigong authored Apr 14, 2025
  
  4ff58b66
- add v0 zero overhead · 54294854
  lizhigong authored Apr 11, 2025
  
  54294854
08 May, 2025 1 commit
- set MOE_NN=1 · e5497373
  zhuwenwen authored May 08, 2025
  
  e5497373
06 May, 2025 1 commit
- support qwen3-moe nn layout · 4dc24bc8
  zhuwenwen authored May 06, 2025
  
  4dc24bc8
30 Apr, 2025 3 commits
- support qwen3 nn layout · 8a12a939
  zhuwenwen authored Apr 30, 2025
  
  8a12a939
- skip apply_rotary_emb from vllm_fa · ffd8e40d
  zhuwenwen authored Apr 30, 2025
  
  ffd8e40d
- skip is_rocm_aiter_moe_enabled and add mla pad · daefd764
  zhuwenwen authored Apr 30, 2025
  
  daefd764
28 Apr, 2025 10 commits
- [Model] Add tuned triton fused_moe configs for Qwen3Moe (#17328) · ba41cc90
  Michael Goin authored Apr 28, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  ba41cc90
- [Model] Qwen3 Dense FP8 Compat Fixes (#17318) · dcbac4cb
  Simon Mo authored Apr 28, 2025
```
Signed-off-by: simon-mo <xmo@berkeley.edu>
```
  dcbac4cb
- [Bugfix] Fix moe weight losing all extra attrs after `process_weights_after_loading`. (#16854) · ed246203
  Charlie Fu authored Apr 28, 2025
```
Signed-off-by: charlifu <charlifu@amd.com>
```
  ed246203
- Explicitly explain quant method override ordering and ensure all overrides are ordered (#17256) · c7941cca
  Harry Mellor authored Apr 28, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  c7941cca
- Make name of `compressed-tensors` quant method consistent across vLLM (#17255) · b6dd32aa
  Harry Mellor authored Apr 28, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  b6dd32aa
- [Misc] Clean up Qwen2.5-Omni code (#17301) · 8b464d96
  Cyrus Leung authored Apr 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  8b464d96
- [Bugfix] Add missing `get_language_model` to new MLLMs (#17300) · 344e193b
  Cyrus Leung authored Apr 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  344e193b
- [Model] Add Granite Speech Support (#16246) · fa93cd9f
  Alex Brooks authored Apr 28, 2025
```
Signed-off-by: Alex-Brooks <Alex.brooks@ibm.com>
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
```
  fa93cd9f
- [Minor][Models] Pass partial_rotary_factor parameter to rope (#17266) · 7fcc4223
  Wanrui Dai authored Apr 28, 2025
```
Signed-off-by: evian <eviantai@u.nus.edu>
Co-authored-by: evian <eviantai@u.nus.edu>
```
  7fcc4223
- [Bugfix] Fix Mistral3 spatial merge error (#17270) · cb3f2d8d
  Michael Goin authored Apr 27, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  cb3f2d8d
27 Apr, 2025 1 commit
- [Bugfix] Fix QWen2 VL multimodal mapping (#17240) · 4283a28c
  Jee Jee Li authored Apr 27, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  4283a28c
26 Apr, 2025 8 commits
- [Minor] Fix lint error in main branch (#17233) · 43eea295
  Woosuk Kwon authored Apr 26, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  43eea295
- [Bugfix] Fix Qwen2.5-Omni M-RoPE position ids generation (#16878) · de7eb10c
  Kero Liang authored Apr 27, 2025
```
Signed-off-by: imkero <kerorek@outlook.com>
```
  de7eb10c
- [V1] Add `structural_tag` support using xgrammar (#17085) · f8acd01f
  Russell Bryant authored Apr 26, 2025
  
  f8acd01f
- [Hardware][Intel-Gaudi] Update hpu-extension and update bucketing system for HPU device (#17186) · c48334d4
  Agata Dobrzyniewicz authored Apr 26, 2025
```
Signed-off-by: Agata Dobrzyniewicz <adobrzyniewicz@habana.ai>
```
  c48334d4
- [ROCm][Misc] Follow-ups for Skinny Gemms on ROCm. (#17011) · 54271bb7
  Charlie Fu authored Apr 26, 2025
```
Signed-off-by: charlifu <charlifu@amd.com>
```
  54271bb7
- [Minor][Models] Fix Return Types of Llama & Eagle (#17220) · b2789112
  Woosuk Kwon authored Apr 25, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  b2789112
- [AMD][FP8][BugFix] Remove V1 check in arg_utils.py for FP8 since it is not necessary (#17215) · 68af5f6c
  rasmith authored Apr 25, 2025
```
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
```
  68af5f6c
- [Bugfix] gemma[2,3] interleaved attention when sliding window is disabled (#17180) · 8de2901f
  Chen Zhang authored Apr 26, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  8de2901f
25 Apr, 2025 8 commits

[V1][Spec Decode] EAGLE-3 Support (#16937) · a0e619e6

Benjamin Chislett authored Apr 25, 2025


Signed-off-by: Bryan Lu <yuzhelu@amazon.com>
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Co-authored-by: Bryan Lu <yuzhelu@amazon.com>

a0e619e6

[Quantization][FP8] Add support for FP8 models with input_scale for output... · a41351f3

rasmith authored Apr 25, 2025


[Quantization][FP8] Add support for FP8 models with input_scale for output projection and QK quantization (#15734)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>

a41351f3

增加per-channel 量化策略支持 · 313d629e
gaoqiong authored Apr 25, 2025

313d629e

[Bugfix] remove fallback in guided_json (int range, patterns) (#16725) · 6aae216b

Sangyeon Cho authored Apr 25, 2025


Signed-off-by: csy1204 <josang1204@gmail.com>
Co-authored-by: 조상연[플레이스 AI] <sang-yeon.cho@navercorp.com>

6aae216b

[Perf]Optimize rotary_emb implementation to use Triton operator for improved... · b22980a1

yexin(叶鑫) authored Apr 25, 2025


[Perf]Optimize rotary_emb implementation to use Triton operator for improved inference performance (#16457)
Signed-off-by: cynthieye <yexin93@qq.com>
Co-authored-by: MagnetoWang <magnetowang@outlook.com>

b22980a1

[Bugfix][Misc] Use TritonPlaceholderModule to defensively import triton (#15099) · 2f540455
Mengqing Cao authored Apr 25, 2025
```
Signed-off-by: Mengqing Cao <cmq0113@163.com>
```
2f540455
fix float16 support for kimi-vl (#17156) · 69bff9bc
Zaida Zhou authored Apr 25, 2025
```
Co-authored-by: zhouzaida <zhouzaida@msh.team>
```
69bff9bc

[FEAT] [ROCm]: AITER Fused MOE V1 Support (#16752) · eef36472

vllmellm authored Apr 25, 2025


Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>

eef36472

24 Apr, 2025 1 commit
- [Misc] Remove OLMo2 config copy (#17066) · b0c1f620
  Isotr0py authored Apr 24, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  b0c1f620