Commits · ad385667103b7a98fee5a4fc46d2a7745407333e · OpenDAS / vllm_cscc · GitLab

16 Oct, 2024 2 commits
- [Kernel][Model] Improve continuous batching for Jamba and Mamba (#9189) · fb60ae9b
  Mor Zusman authored Oct 17, 2024
  
  fb60ae9b
- [Misc] Standardize RoPE handling for Qwen2-VL (#9250) · 7e7eae33
  Cyrus Leung authored Oct 16, 2024
  
  7e7eae33
11 Oct, 2024 1 commit
- [Model] Support Mamba (#6484) · 7342a7d7
  Tyler Michael Smith authored Oct 11, 2024
  
  7342a7d7
10 Oct, 2024 1 commit
- [Bugfix] Machete garbage results for some models (large K dim) (#9212) · a64e7b94
  Lucas Wilkinson authored Oct 10, 2024
  
  a64e7b94
09 Oct, 2024 1 commit
- update test_prefix_prefill.py · ec417173
  zhuwenwen authored Oct 09, 2024
  
  ec417173
08 Oct, 2024 1 commit
- [Bugfix] Try to handle older versions of pytorch (#9086) · bd37b9fb
  bnellnm authored Oct 08, 2024
  
  bd37b9fb
04 Oct, 2024 1 commit
- [Kernel] Zero point support in fused MarlinMoE kernel + AWQ Fused MoE (#8973) · 05d68643
  ElizaWszola authored Oct 04, 2024
```
Co-authored-by: Dipika <dipikasikka1@gmail.com>
Co-authored-by: Dipika Sikka <ds3822@columbia.edu>
```
  05d68643
03 Oct, 2024 1 commit
- [misc] add forward context for attention (#9029) · 9aaf14c6
  youkaichao authored Oct 03, 2024
  
  9aaf14c6
29 Sep, 2024 2 commits
- [Kernel][Model] Varlen prefill + Prefill chunking support for mamba kernels and Jamba model (#8533) · f13a07b1
  Mor Zusman authored Sep 30, 2024
  
  f13a07b1
- [Bugfix] Fix Marlin MoE act order when is_k_full == False (#8741) · d081da00
  ElizaWszola authored Sep 29, 2024
```
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  d081da00
27 Sep, 2024 1 commit
- [torch.compile] use empty tensor instead of None for profiling (#8875) · a9b15c60
  youkaichao authored Sep 27, 2024
  
  a9b15c60
25 Sep, 2024 1 commit
- [Kernel] Fullgraph and opcheck tests (#8479) · 300da091
  bnellnm authored Sep 25, 2024
  
  300da091
23 Sep, 2024 1 commit

[Kernel] (2/N) Machete - Integrate into CompressedTensorsWNA16 and GPTQMarlin (#7701) · 86e9c8df

Lucas Wilkinson authored Sep 23, 2024

Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

86e9c8df

19 Sep, 2024 1 commit
- [Kernel][Amd] Add fp8 kv cache support for rocm custom paged attention (#8577) · 9cc373f3
  Charlie Fu authored Sep 19, 2024
  
  9cc373f3
18 Sep, 2024 2 commits
- [Kernel] Change interface to Mamba selective_state_update for continuous batching (#8039) · db9120cd
  Tyler Michael Smith authored Sep 18, 2024
  
  db9120cd
- [CI/Build] Avoid CUDA initialization (#8534) · 6ffa3f31
  Cyrus Leung authored Sep 18, 2024
  
  6ffa3f31
17 Sep, 2024 2 commits
- [Kernel] Change interface to Mamba causal_conv1d_update for continuous batching (#8012) · 8110e445
  Tyler Michael Smith authored Sep 17, 2024
  
  8110e445
- [refactor] remove triton based sampler (#8524) · 546034b4
  Simon Mo authored Sep 16, 2024
  
  546034b4
16 Sep, 2024 2 commits
- [Kernel] AQ AZP 3/4: Asymmetric quantization kernels (#7270) · 5d73ae49
  Luka Govedič authored Sep 16, 2024
  
  5d73ae49
- [Kernel] Enable 8-bit weights in Fused Marlin MoE (#8032) · a091e2da
  ElizaWszola authored Sep 16, 2024
```
Co-authored-by: Dipika <dipikasikka1@gmail.com>
```
  a091e2da
15 Sep, 2024 1 commit
- [Bugfix][Kernel] Add `IQ1_M` quantization implementation to GGUF kernel (#8357) · fc990f97
  Isotr0py authored Sep 16, 2024
  
  fc990f97
14 Sep, 2024 1 commit
- [Kernel][Hardware][Amd]Custom paged attention kernel for rocm (#8310) · 1ef0d2ef
  Charlie Fu authored Sep 13, 2024
  
  1ef0d2ef
13 Sep, 2024 1 commit
- [CI/Build] Reorganize models tests (#7820) · a84e598e
  Cyrus Leung authored Sep 14, 2024
  
  a84e598e
11 Sep, 2024 1 commit
- [Kernel][Misc] register ops to prevent graph breaks (#6917) · 73202dbe
  bnellnm authored Sep 11, 2024
```
Co-authored-by: Sage Moore <sage@neuralmagic.com>
```
  73202dbe
10 Sep, 2024 1 commit
- [Misc] Fused MoE Marlin support for GPTQ (#8217) · 6cd5e5b0
  Dipika Sikka authored Sep 09, 2024
  
  6cd5e5b0
06 Sep, 2024 1 commit
- update tests · be0967c1
  zhuwenwen authored Sep 06, 2024
  
  be0967c1
05 Sep, 2024 1 commit
- [Core/Bugfix] Add query dtype as per FlashInfer API requirements. (#8173) · e39ebf5c
  Elfie Guo authored Sep 04, 2024
  
  e39ebf5c
29 Aug, 2024 2 commits
- [Core][Kernels] Enable FP8 KV Cache with Flashinfer backend. + BugFix for... · 6b342156
  Pavani Majety authored Aug 29, 2024
```
[Core][Kernels] Enable FP8 KV Cache with Flashinfer backend.  + BugFix for kv_cache_dtype=auto (#7985)
Co-authored-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
```
  6b342156
- Revert "[Core][Kernels] Use FlashInfer backend for FP8 KV Cache when available." (#7982) · ef99a787
  youkaichao authored Aug 28, 2024
  
  ef99a787
28 Aug, 2024 3 commits
- [Kernel/Model] Migrate mamba_ssm and causal_conv1d kernels to vLLM (#7651) · fdd9daaf
  Mor Zusman authored Aug 29, 2024
  
  fdd9daaf
- [Kernel] [Triton] [AMD] Adding Triton implementations awq_dequantize and... · e5697d16
  rasmith authored Aug 28, 2024
```
[Kernel] [Triton] [AMD] Adding Triton implementations awq_dequantize and awq_gemm to support AWQ (#7386)
```
  e5697d16
- [Core][Kernels] Use FlashInfer backend for FP8 KV Cache when available. (#7798) · b98cc28f
  Pavani Majety authored Aug 28, 2024
```
Co-authored-by: Simon Mo <simon.mo@hey.com>
```
  b98cc28f
21 Aug, 2024 2 commits
- [BUG] fix crash on flashinfer backend with cudagraph disabled, when attention... · 53328d75
  LI MOU authored Aug 21, 2024
```
[BUG] fix crash on flashinfer backend with cudagraph disabled, when attention group_size not in [1,2,4,8] (#7509)
```
  53328d75
- fix tests and update the usage of fa · 1c18cce0
  zhuwenwen authored Aug 21, 2024
  
  1c18cce0
20 Aug, 2024 2 commits
- [Kernel] (1/N) Machete - Hopper Optimized Mixed Precision Linear Kernel (#7174) · 5288c06a
  Lucas Wilkinson authored Aug 20, 2024
  
  5288c06a
- fix fa and triton tests · 3a6764a4
  zhuwenwen authored Aug 20, 2024
  
  3a6764a4
16 Aug, 2024 3 commits
- [Feature][Hardware][Amd] Add fp8 Linear Layer for Rocm (#7210) · e837b624
  Charlie Fu authored Aug 16, 2024
  
  e837b624
- register custom op for flash attn and use from torch.ops (#7536) · 54bd9a03
  youkaichao authored Aug 15, 2024
  
  54bd9a03
- [Misc/Testing] Use `torch.testing.assert_close` (#7324) · 50b8d08d
  jon-chuang authored Aug 15, 2024
  
  50b8d08d
12 Aug, 2024 1 commit
- [Core/Bugfix] Add FP8 K/V Scale and dtype conversion for prefix/prefill Triton Kernel (#7208) · a046f863
  jon-chuang authored Aug 12, 2024
```
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
```
  a046f863