[Version] Bump version to 0.2.76

[CharlieFRuan]

Change

• https://github.com/mlc-ai/web-llm/pull/635
  • Integrate with web-xgrammar
  • Support ResponseFormat.type == "grammar", where you specify an EBNF grammar string
  • Add grammar_init_ms and grammar_per_token_ms to CompletionUsage.extra when using grammar
  • Add time_to_first_token_s (TTFT) and time_per_output_token_s (TPOT), e2e_latency_s to CompletionUsage.extra
  • Add ignore_eos to Completion and ChatCompletion requests
• https://github.com/mlc-ai/web-llm/pull/632
  • Fixes of vram requirement for Qwen2.5-Coder-1.5B-Instruct model

TVMjs

• No change, version 0.18.0-dev2 just like 0.2.71