Skip to content
View SheridanLu's full-sized avatar

Block or report SheridanLu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Popular repositories Loading

  1. glm53-flash-a40-fp8kv glm53-flash-a40-fp8kv Public

    GLM-5.3-Flash AWQ on 8xA40 (sm_86): NoPE FP8 KV cache port (528 B/token, 1.85x KV), patch dry-run notes, concurrent canary monitor, tests + raw logs. Experimental.

    Python 1

  2. qwen38-flash-next-a40 qwen38-flash-next-a40 Public

    Serving Qwen3.8-Flash-Next (FP8) on 8x A40 (sm_86) with vLLM: version matrix (0.31 works, 0.32/0.33 do not), production config, microbenchmarks, negative results.

    Python 1

  3. over-persistence-ct-lesions-repro over-persistence-ct-lesions-repro Public

    TeX

  4. glm53-flash-a40-sglang-dflash2 glm53-flash-a40-sglang-dflash2 Public

    GLM-5.3-Flash (NVFP4) with SGLang + DFlash2 speculative decoding on 8xA40: launch recipe, passive metrics sampler, concurrency/acceptance analysis

    Python