[Fix] fix offline env use local mode path (#22526)

rongfu.leng committed about 1 year ago

[Model] Improve olmo and olmo2 (#23228)

Jee Jee Li committed about 1 year ago

[Model][V1] Support Ernie MTP (#22169)

xyxinyang committed about 1 year ago

Update to flashinfer-python==0.2.12 and disable AOT compile for non-release image (#23129)

Michael Goin committed about 1 year ago

[Bugfix] Ensure correctness of Cohere2Vision processing (#23245)

Cyrus Leung committed about 1 year ago

[Model] Support deepseek with eagle (#21086)

Xin Yang committed about 1 year ago

Fix missing quotes (#23242)

Shiming Zhang committed about 1 year ago

[Model] use autoWeightsLoader for gptoss (#22446)

Calvin Chen committed about 1 year ago

fix cuda graph (#22721)

who who who committed about 1 year ago

[BugFix] Fix stuck stats/metrics after requests are aborted (#22995)

Nick Hill committed about 1 year ago

[CI/Build] Sync multimodal tests (#23181)

Cyrus Leung committed about 1 year ago

[CI/Build] Also check DP in benchmarks throughput script (#23038)

Zhewen Li committed about 1 year ago

chore: support pytorch format in lora (#22790)

길재은 committed about 1 year ago

Fix a performance comparison issue in Benchmark Suite (#23047)

Louie Tsai committed about 1 year ago

[Attention] Optimize make_local_attention_virtual_batches for Flash Attention (#23185)

Zebing Lin committed about 1 year ago

[Doc] Update V1 status of various pooling models (#23189)

Cyrus Leung committed about 1 year ago

[Core] Add torch profiler CPU traces for AsyncLLM. (#21794)

Chenheli Hua committed about 1 year ago

[CI Perf] Only test bfloat16 for tests/compile/test_fusion_all_reduce.py (#23132)

Michael Goin committed about 1 year ago

[Core] Optimize scheduler request removal for single completions (#21917)

633WHU committed about 1 year ago

[Quantization] Bump Compressed Tensors Version (#23202)

Kyle Sayers committed about 1 year ago