vLLM/vllm/model_executor at c01368fd64eaecc0c7242e4d933ec80fe8e047f5 - vLLM

Files

T

$HDCharles <{"message":"Not Found","documentation_url":"https://docs.github.com/rest/users/emails#list-email-addresses-for-the-authenticated-user","status":"404"}>$

c01368fd64 [Quant] Use canonical N-first weight format for CT WNA16 MoE (#52798 )

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: HDCharles <{"message":"Not Found","documentation_url":"https://docs.github.com/rest/users/emails#list-email-addresses-for-the-authenticated-user","status":"404"}>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>

2026-09-28 11:22:44 -06:00

determinism

[Bugfix] batch_invariant: keep non-AllReduce collectives enabled on NCCL >= 2.31 (#58179 )

2026-09-22 14:44:00 -04:00

hw_agnostic

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212 )

2026-09-16 10:57:24 -07:00

kernels

[ROCm][Perf] Replace torch.topk in DSA candidate block selection (#58208 )

2026-09-28 10:42:42 -05:00

layers

[Quant] Use canonical N-first weight format for CT WNA16 MoE (#52798 )