Commits · e835a50021e03bf7c14b8af68b210189bb6e768b · change / sglang

23 Dec, 2024 1 commit
- Reorg moe code (#2563) · e835a500
  Ke Bao authored Dec 24, 2024
  
  e835a500
06 Dec, 2024 1 commit
- Resubmit MoE-EP (#2371) · 3d32e4a3
  xiaobochen authored Dec 06, 2024
  
  3d32e4a3
05 Dec, 2024 1 commit
- Fix AWQ with enable MLA (#2364) · 4a63c181
  Ke Bao authored Dec 06, 2024
  
  4a63c181
04 Dec, 2024 1 commit
- MLA prefill w/o weight absorption (#2349) · ec52464d
  Ke Bao authored Dec 05, 2024
  
  ec52464d
02 Dec, 2024 1 commit
- Update model_loader deps and qqq quantization deps (#2220) (#2318) · 85e1a6f3
  Yineng Zhang authored Dec 02, 2024
```
Co-authored-by: HandH1998 <1335248067@qq.com>
```
  85e1a6f3
01 Dec, 2024 2 commits
- Revert "Revert "[FEAT] Support GGUF format"" (#2287) · 4936be8a
  Lianmin Zheng authored Nov 30, 2024
  
  4936be8a
- Revert "[FEAT] Support GGUF format" (#2285) · 7e4c6dd8
  Lianmin Zheng authored Nov 30, 2024
  
  7e4c6dd8
30 Nov, 2024 1 commit
- [FEAT] Support GGUF format (#2215) · 883c9554
  Yang Zheng authored Nov 30, 2024
```
Co-authored-by: Yang Zheng(SW)(Alex) <you@example.com>
```
  883c9554
24 Nov, 2024 2 commits
- Rename triton_fused_moe -> fused_moe_triton (#2163) · be0124bd
  Lianmin Zheng authored Nov 24, 2024
  
  be0124bd
- feat: remove the dependency on FusedMoE (#2153) · b509db58
  Yineng Zhang authored Nov 24, 2024
  
  b509db58
22 Nov, 2024 1 commit
- docs: fix module docstrings and copyright headers (#2077) · 62a4a339
  Xuehai Pan authored Nov 22, 2024
  
  62a4a339
16 Nov, 2024 1 commit
- Support DP MLA (#1970) · 976bc302
  Ke Bao authored Nov 16, 2024
  
  976bc302
01 Nov, 2024 1 commit
- Update vocab embedding deps and add TP switch (#1856) · 16eb33ff
  Ke Bao authored Nov 01, 2024
  
  16eb33ff
20 Oct, 2024 1 commit
- Update vllm to 0.6.3 (#1711) (#1720) · 8bee20f8
  Yineng Zhang authored Oct 19, 2024
```
Co-authored-by: Ke Bao <ISPObaoke@163.com>
```
  8bee20f8
14 Oct, 2024 1 commit
- [1/N] Remove `CacheConfig` import in all model files (#1658) · 56503d9b
  Byron Hsu authored Oct 14, 2024
  
  56503d9b
07 Oct, 2024 1 commit
- Use is_flashinfer_available to replace is_hip for flashinfer check (#1596) · 6a5b352a
  Lianmin Zheng authored Oct 06, 2024
```
Co-authored-by: Zhang Liangang <liangang.zhang@intel.com>
```
  6a5b352a
30 Sep, 2024 1 commit
- Rename InputMetadata -> ForwardBatch (#1543) · 36d5acfc
  Lianmin Zheng authored Sep 30, 2024
  
  36d5acfc
19 Sep, 2024 1 commit
- feat: update linear deps 1/N (#1305) · b4408b0d
  Yineng Zhang authored Sep 19, 2024
  
  b4408b0d
17 Sep, 2024 3 commits
- Enable MLA by default (#1447) · c6b6d2e7
  Ke Bao authored Sep 17, 2024
  
  c6b6d2e7
- Fix torch compile for deepseek-v2 (#1442) · 76524b70
  Ke Bao authored Sep 17, 2024
  
  76524b70
- [Feature, Hardware] Enable SGLang on AMD GPUs via PyTorch for ROCm (#1420) · 3a6e0418
  HAI authored Sep 17, 2024
  
  3a6e0418
14 Sep, 2024 1 commit
- Optimize conflicts between CUDA graph and vocab mask tensors (#1392) · 70b68029
  Liangsheng Yin authored Sep 13, 2024
  
  70b68029
01 Sep, 2024 1 commit
- feat: fix fp8 for MLA and support bmm fp8 for DeepSeek V2 (#1285) · 54772f78
  Yineng Zhang authored Sep 01, 2024
```
Co-authored-by: ispobock <ispobaoke@163.com>
```
  54772f78
31 Aug, 2024 1 commit
- fix: resolve the fp8 bug introduced by vLLM 0.5.5 (#1276) · 52cefdbf
  Yineng Zhang authored Sep 01, 2024
  
  52cefdbf
30 Aug, 2024 1 commit
- Transpose mla weight offline (#1261) · f414352a
  Ke Bao authored Aug 30, 2024
```
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  f414352a
29 Aug, 2024 1 commit
- Sampler cudagraph (#1253) · 381dd57b
  Liangsheng Yin authored Aug 28, 2024
  
  381dd57b
28 Aug, 2024 1 commit
- hotfix: revert sampler CUDA Graph (#1242) · f25f4dfd
  Yineng Zhang authored Aug 28, 2024
  
  f25f4dfd
26 Aug, 2024 1 commit
- Move sampler into CUDA graph (#1201) · 75ce37f4
  Liangsheng Yin authored Aug 26, 2024
```
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  75ce37f4
13 Aug, 2024 1 commit
- Fix layernorm input shape (#1066) · 162f3ccb
  Ke Bao authored Aug 13, 2024
```
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  162f3ccb
12 Aug, 2024 1 commit
- feat: replace all rmsnorm and silu (#1057) · 6a38efa8
  Yineng Zhang authored Aug 13, 2024
  
  6a38efa8
07 Aug, 2024 1 commit
- Organize code (rename, movement) (#953) · 87e8c090
  Liangsheng Yin authored Aug 06, 2024
  
  87e8c090
04 Aug, 2024 1 commit
- Support MLA for DeepSeek-V2 with Triton - step 1 (#905) · e1eae1fd
  Ke Bao authored Aug 05, 2024
  
  e1eae1fd
30 Jul, 2024 1 commit
- Code structure refactor (#807) · cdcbde5f
  Liangsheng Yin authored Jul 29, 2024
  
  cdcbde5f
28 Jul, 2024 1 commit
- chore: add copyright for srt (#790) · dd7e8b94
  Yineng Zhang authored Jul 28, 2024
  
  dd7e8b94
27 Jul, 2024 1 commit
- Deepseek v2 support (#693) · 679ebcbb
  Liangsheng Yin authored Jul 26, 2024
  
  679ebcbb
17 Jul, 2024 1 commit
- misc: add pre-commit config (#637) · 2e341cd4
  zhyncs authored Jul 18, 2024
  
  2e341cd4
16 Jul, 2024 1 commit
- Fix model forward grad (#628) · c9ee3d35
  Liangsheng Yin authored Jul 15, 2024
  
  c9ee3d35
14 Jul, 2024 1 commit
- Optimize mem indices mangement (#619) · 564a898a
  Liangsheng Yin authored Jul 13, 2024
  
  564a898a
09 Jul, 2024 1 commit
- Add Qwen2 MoE support (#603) · 740c46a1
  Tommy Yang authored Jul 09, 2024
  
  740c46a1