Commits · fc78640e00e39520fa7126789d23369d2f104d0c · change / sglang

"sgl-kernel/python/sgl_kernel/load_utils.py" did not exist on "616a3e20df5faf73a7d1581c7016413f64d583e4"

01 Dec, 2024 9 commits
- minor: support flashinfer nightly (#2295) · fc78640e
  Yineng Zhang authored Dec 01, 2024
  
  fc78640e
- Feat: upgrade outlines & support compatibility with the old version (#2292) · 906d795f
  gobraves authored Dec 01, 2024
  
  906d795f
- feat: add should_use_tensor_core (#2179) · 118b6af3
  Yineng Zhang authored Dec 01, 2024
  
  118b6af3
- Fix chunked prefill when ignore eos (#2290) · 5f12f0e7
  Liangsheng Yin authored Dec 01, 2024
  
  5f12f0e7
- adapt vllm distributed module to sglang (#2244) · d5b95cbb
  yizhang2077 authored Dec 01, 2024
```
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  d5b95cbb
- Revert "Revert "[FEAT] Support GGUF format"" (#2287) · 4936be8a
  Lianmin Zheng authored Nov 30, 2024
  
  4936be8a
- Revert "[Fix] fix assertion error for chunked prefill when disabling cache" (#2286) · f5b5f2bf
  Lianmin Zheng authored Nov 30, 2024
  
  f5b5f2bf
- Revert "[FEAT] Support GGUF format" (#2285) · 7e4c6dd8
  Lianmin Zheng authored Nov 30, 2024
  
  7e4c6dd8
- [Fix] fix assertion error for chunked prefill when disabling cache (#2282) · d622851d
  Rui Wang authored Dec 01, 2024
  
  d622851d
30 Nov, 2024 6 commits
- [FEAT] Support GGUF format (#2215) · 883c9554
  Yang Zheng authored Nov 30, 2024
```
Co-authored-by: Yang Zheng(SW)(Alex) <you@example.com>
```
  883c9554
- [CI] Print summary on github actions (#2274) · ccaf1f99
  Lianmin Zheng authored Nov 29, 2024
  
  ccaf1f99
- Add get weights by parameter name for llama (#2266) · 7d1485d3
  Chayenne authored Nov 29, 2024
  
  7d1485d3
- udate weights from disk (#2265) · 7d5d1d3d
  Chayenne authored Nov 29, 2024
  
  7d5d1d3d
- Support LoRA in Completion API (#2243) · 01017d4c
  bjmsong authored Nov 30, 2024
```
Co-authored-by: root <bjmsong@126.com>
```
  01017d4c
- Fix the default chunked prefill size (#2268) · 94e167ea
  Lianmin Zheng authored Nov 29, 2024
  
  94e167ea
29 Nov, 2024 7 commits
- [benchmark] Add fused_moe_triton benchmark and tuning tools (#2225) · 262e370f
  Xiaoyu Zhang authored Nov 30, 2024
```
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: HAI <hixiao@gmail.com>
```
  262e370f
- chore: bump v0.3.6.post3 (#2259) · fae4e5e9
  Yineng Zhang authored Nov 30, 2024
  
  fae4e5e9
- [Minor] fix the style for multimodal models (#2257) · afe1e465
  Lianmin Zheng authored Nov 29, 2024
  
  afe1e465
- Fix hash collision for multi modal models (#2256) · f50a6cf4
  Lianmin Zheng authored Nov 29, 2024
  
  f50a6cf4
- Simplify tokenizer manager (#2254) · fe97a2d4
  Lianmin Zheng authored Nov 29, 2024
  
  fe97a2d4
- Revert "Revert "Add simple CPU offloading support"" (#2253) · 8b48496a
  Ying Sheng authored Nov 28, 2024
```
Co-authored-by: Jani Monoses <jani.monoses@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  8b48496a
- Revert "Add simple CPU offloading support" (#2252) · 4057ea82
  Ying Sheng authored Nov 28, 2024
```
We'll re-add the commit to correctly ack Kaichao's authorship
```
  4057ea82
28 Nov, 2024 8 commits
- [fix] Fix prefix caching for multi-image/video (#2239) · b7038fec
  Ying Sheng authored Nov 28, 2024
  
  b7038fec
- fix missing launch server import (#2242) · 65fdb289
  Enrique Shockwave authored Nov 28, 2024
  
  65fdb289
- Fix memory leak during abort (#2238) · b2ccf36d
  Lianmin Zheng authored Nov 28, 2024
  
  b2ccf36d
- Crash the server correctly during error (#2231) · d4fc1a70
  Lianmin Zheng authored Nov 28, 2024
  
  d4fc1a70
- Add OLMo2 model. (#2233) · db674e3d
  Jani Monoses authored Nov 28, 2024
  
  db674e3d
- Disable overlap scheduler for multimodal models (#2235) · fb915bd1
  Lianmin Zheng authored Nov 27, 2024
  
  fb915bd1
- Fix chunked prefill size for bench_offline_throughput (#2234) · 09798b36
  Lianmin Zheng authored Nov 27, 2024
  
  09798b36
- Rename tuned MI300X config files for fused_moe_triton (#2228) · cd51758f
  HAI authored Nov 27, 2024
  
  cd51758f
27 Nov, 2024 10 commits
- add profile in offline benchmark & update doc (#2123) · 91e5dbf5
  bjmsong authored Nov 28, 2024
```
Co-authored-by: root <bjmsong@126.com>
```
  91e5dbf5
- Remove fused_moe_grok (#2223) · dd5eba4c
  Lianmin Zheng authored Nov 27, 2024
  
  dd5eba4c
- fix typo prompts (#2224) · a4fd2f9b
  Baoyuan Qi authored Nov 28, 2024
  
  a4fd2f9b
- Rename DP_RANK to SGLANG_DP_RANK (#2218) · 2a02185c
  Lianmin Zheng authored Nov 27, 2024
  
  2a02185c
- Release v0.3.6.post2 (#2214) · fed4c694
  Lianmin Zheng authored Nov 27, 2024
```
Co-authored-by: Yineng Zhang <me@zhyncs.com>
```
  fed4c694
- Use an env var SGLANG_SET_CPU_AFFINITY to set cpu affinity; turn it off by default (#2222) · fb6e04a0
  Lianmin Zheng authored Nov 27, 2024
  
  fb6e04a0
- Revert "Use an env var SGLANG_SET_CPU_AFFINITY to set cpu affinity; turn it off by default" (#2221) · 6997e28f
  Lianmin Zheng authored Nov 27, 2024
  
  6997e28f
- Use an env var SGLANG_SET_CPU_AFFINITY to set cpu affinity; turn it off by default (#2217) · a0e58740
  Lianmin Zheng authored Nov 27, 2024
  
  a0e58740
- [feat] Support session control for vision language models (#2210) · 37c8a576
  Ying Sheng authored Nov 27, 2024
  
  37c8a576
- Fix flasky tests (#2212) · c754652f
  Lianmin Zheng authored Nov 26, 2024
  
  c754652f