[Model] Fix bagel failed to run (#31132)

Li Wang committed 11 months ago

Update MiniMax-M2 ToolCall and add MiniMax-M2.1 in Docs (#31083)

Roger Young committed 11 months ago

[Bugfix][ROCm] Fix typo: is_linear_fp8_enaled -> is_linear_fp8_enabled (#31109)

Kevin McKay committed 11 months ago

[Misc] Fix typo: 'occured' -> 'occurred' (#31120)

Kevin McKay committed 11 months ago

[Misc] Fix spelling typos in model comments (#31117)

Kevin McKay committed 11 months ago

[Misc] Fix grammar errors in comments and messages (#31115)

Kevin McKay committed 11 months ago

[Misc] Fix quantization-related typos (#31116)

Kevin McKay committed 11 months ago

[Misc] Fix spelling typos in comments (#31114)

Kevin McKay committed 11 months ago

[Feature]: Support NVIDIA ModelOpt HF FP8 variants FP8_PER_CHANNEL_PER_TOKEN and FP8_PB_WO in vLLM (#30957)

CedricHuang committed 11 months ago

[Kernel] Enable fused_qknorm_rope_kernel supports partial rope (#30821)

Jee Jee Li committed 11 months ago

[CI] Fix "2 Node Tests (4 GPUs in total)" (#31090)

Lucas Wilkinson committed 11 months ago

[Doc] Clarify FP8 KV cache computation workflow (#31071)

Steve Westerhouse committed 11 months ago

[NVFP4][Perf] Tune NVFP4 input quant kernel for small batch size (#30897)

Michael Goin committed 11 months ago

[MoE Refactor][4/N] Marlin Fp8 Mk (#31036)

Robert Shaw committed 11 months ago

ci: add nvidia-smi warmup before Prime-RL integration test (#31093)

Ameen Patel committed 11 months ago

add aarnphm and chaunceyjiang to the new tool_parser directory (#31088)

Chauncey committed 11 months ago

[BugFix]fix gpt-oss v1/completions response bug (#30608)

汪志鹏 committed 11 months ago

[Quantization] add marlin w4a8/w8a8 check (#31061)

Jinzhen Lin committed 11 months ago

[CI] Fix H200 Distributed test (#31054)

Lucas Wilkinson committed 11 months ago

[Quantization] support logical_widths for fp8 marlin (#30962)

Jinzhen Lin committed 11 months ago