Commits · bc1f6fda0d479ebf26b32d31f9835a5d8f05e1ef · change / sglang

"test/git@developer.sourcefind.cn:change/sglang.git" did not exist on "c7d57d5bb32d16e2ce079b57dce780867aab6e6e"

26 Nov, 2024 8 commits
- fix: add cuda-python for xgrammar (#2199) · bc1f6fda
  Yineng Zhang authored Nov 26, 2024
  
  bc1f6fda
- using `is not` not `!=` to test `None` (#2196) · 867e092f
  Wang Ran (汪然) authored Nov 26, 2024
  
  867e092f
- Remove unresolved reference 'self' (#2198) · 88c7763f
  Andrew Lyu authored Nov 26, 2024
  
  88c7763f
- remove unused imports (#2195) · e4118b15
  Wang Ran (汪然) authored Nov 26, 2024
  
  e4118b15
- Update sampler.py to skip the success check (#2197) · ba4ee37f
  Lianmin Zheng authored Nov 26, 2024
  
  ba4ee37f
- Release v0.3.6.post1 (#2189) · ac5a0f04
  Lianmin Zheng authored Nov 25, 2024
  
  ac5a0f04
- [CI] Minor fix for CI (#2187) · 1605ae12
  Lianmin Zheng authored Nov 25, 2024
  
  1605ae12
- Input_embeds support (#2052) · 1aea19f6
  Rin Intachuen authored Nov 25, 2024
  
  1aea19f6
25 Nov, 2024 10 commits
- Update XGrammar to the latest API (#2176) · 7f076c2c
  Yixin Dong authored Nov 25, 2024
```
Co-authored-by: Ben Gitter <gitterbd@gmail.com>
```
  7f076c2c
- Update CI threshold (#2186) · 3c5538f7
  Lianmin Zheng authored Nov 25, 2024
  
  3c5538f7
- [Performance]: Process affinity to CPU cores with multiple sockets support (#2171) · 10189d08
  HAI authored Nov 25, 2024
  
  10189d08
- Use custom allreduce w/ torch.compile (#2185) · c4336b2b
  Lianmin Zheng authored Nov 25, 2024
  
  c4336b2b
- [feat] Refactor session control interface and add CI (#2173) · e1e595d7
  Ying Sheng authored Nov 25, 2024
  
  e1e595d7
- [Fix] Avoid calling fill_vocab_mask for terminated requests (#2175) · 538fa0ae
  Yixin Dong authored Nov 25, 2024
  
  538fa0ae
- feat: fused_moe fp8 monkey patch (#2174) · 55842eb8
  Yineng Zhang authored Nov 25, 2024
  
  55842eb8
- Replace prob based with threshold based load balancing (#2170) · 4b0a1c93
  Byron Hsu authored Nov 24, 2024
  
  4b0a1c93
- Allow overwrite flashinfer use_tensorcore (#2169) · 8e1adb84
  Lianmin Zheng authored Nov 24, 2024
  
  8e1adb84
- [Fused moe] add tuning fused configs for qwen2 57b and mixtral 8x7b (#2167) · dd44173d
  Xiaoyu Zhang authored Nov 25, 2024
  
  dd44173d
24 Nov, 2024 10 commits
- Rename triton_fused_moe -> fused_moe_triton (#2163) · be0124bd
  Lianmin Zheng authored Nov 24, 2024
  
  be0124bd
- Fix mixed chunked prefill in overlap mode (#2158) · 731146f6
  Lianmin Zheng authored Nov 24, 2024
  
  731146f6
- fix: use torch.sum for compatible (#2161) · fa271613
  Yineng Zhang authored Nov 24, 2024
  
  fa271613
- Update CI threshold & Improve code style (#2159) · 5652c565
  Lianmin Zheng authored Nov 24, 2024
  
  5652c565
- feat: update other MoE models deps (#2156) · e3938b2f
  Yineng Zhang authored Nov 24, 2024
  
  e3938b2f
- Simplify batch update (#2154) · c211e7b6
  Lianmin Zheng authored Nov 24, 2024
  
  c211e7b6
- fix: resolve end-of-file-fixer (#2157) · d90c3d6b
  Yineng Zhang authored Nov 24, 2024
  
  d90c3d6b
- feat: update gitignore and add tuning config for FusedMoE (#2155) · 9e8f8fbf
  Yineng Zhang authored Nov 24, 2024
  
  9e8f8fbf
- feat: remove the dependency on FusedMoE (#2153) · b509db58
  Yineng Zhang authored Nov 24, 2024
  
  b509db58
- Merged three native APIs into one: get_server_info (#2152) · dbe17293
  Henry Hyeonmok Ko authored Nov 24, 2024
  
  dbe17293
23 Nov, 2024 9 commits
- fix dp_rank env (#2144) · 52f58fc4
  Byron Hsu authored Nov 23, 2024
  
  52f58fc4
- [router] cache-aware load-balancing router v1 (#2114) · cbedd1db
  Byron Hsu authored Nov 23, 2024
  
  cbedd1db
- fix: resolve bench_serving args (#2139) · ad47749b
  Yineng Zhang authored Nov 23, 2024
  
  ad47749b
- Fix dp print message (#2138) · 751c3a03
  Lianmin Zheng authored Nov 23, 2024
  
  751c3a03
- Add concurrency option for benchmark (#2136) · 60769be1
  Yunmeng authored Nov 23, 2024
  
  60769be1
- [CI] Fix test cases (#2137) · a78d8f8d
  Lianmin Zheng authored Nov 23, 2024
  
  a78d8f8d
- Fix grid size in Triton decoding kernel (#2134) · c5f86501
  Ke Bao authored Nov 23, 2024
  
  c5f86501
- Add simple CPU offloading support. (#2081) · d98fa1e9
  Jani Monoses authored Nov 23, 2024
  
  d98fa1e9
- Add initial support for intel Gaudi accelerators (#2121) · 865233e2
  Ankur Neog authored Nov 23, 2024
  
  865233e2
22 Nov, 2024 3 commits
- Revert "Only stream output on tp rank 0" (#2130) · 66d4859a
  Lianmin Zheng authored Nov 22, 2024
  
  66d4859a
- Only stream output on tp rank 0 (#2124) · e1b63624
  Lianmin Zheng authored Nov 22, 2024
  
  e1b63624
- Expose max total num tokens from Runtime & Engine API (#2092) · c35cd1f8
  Henry Hyeonmok Ko authored Nov 22, 2024
  
  c35cd1f8