Ziming Mao

icon indicating a website link https://maoziming.github.io/ icon indicating an email [email protected]

icon company UC Berkeley icon location Berkeley, CA icon location PhD student @ UC Berkeley at @ucbrise and @NetSys, CS @ Yale, @Yale-LILY, @Thesys-lab @ CMU. Prev. @Databricks

Results 4 comments of Ziming Mao

Running simple-cache-example gives an error, flag 'v' was defined more than once

Same problem

Getting TLS to work with Rust client

@pingyu Thanks I believe I am on the latest commit

[Bug] Running DeepSeek-R1 on B200

The current nightly `FROM lmsysorg/sglang:nightly-dev-cu13-20251116-de7eaa7c` still gives the same issue ``` File "/usr/local/lib/python3.12/dist-packages/flashinfer/fused_moe/core.py", line 1379, in trtllm_fp8_block_scale_moe_op moe_op.trtllm_fp8_block_scale_moe( File "python/tvm_ffi/cython/function.pxi", line 901, in core.Function.__call__ TypeError: Mismatched type on argument #17...

`notify_dispatch` and `cached_notify` in normal mode.

Thanks for the answer. What do you mean by "written to disk"? I am wondering why low latency mode does not need these primitives